{"_id":"clawmem","_rev":"89-723365c0eb398c208976f68093ea9a51","name":"clawmem","dist-tags":{"latest":"0.41.3"},"versions":{"0.1.0":{"name":"clawmem","version":"0.1.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.1.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"f22ab8ed6528b7e2da9f97d50126229fb8b4143c","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.1.0.tgz","fileCount":50,"integrity":"sha512-8jbQEuZWwIEvSLf2V0j6QZGnnZ6pFpETj9wnQcFxwjpwHQJy5zKI187eqMTmekGf480qnKDHs2YFsfdHTxktew==","signatures":[{"sig":"MEQCIBrP/C1maOtZeERRsWORE2dFJyymV7KyKIt1Q+U2mGc3AiA2EUznSWlNGoV0Vx8dwBIOtutr94HRHYCwb2eWiuO7yA==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":856055},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"467d20261587460643fea4ea7523d210cb8e4865","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"10.8.2","description":"On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.1.0_1773574785210_0.1009892465389759","host":"s3://npm-registry-packages-npm-production"}},"0.1.1":{"name":"clawmem","version":"0.1.1","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.1.1","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"a4e2551385c6c8b91e77136147ddfaf5a8042521","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.1.1.tgz","fileCount":50,"integrity":"sha512-R7GqI3iv5KGtMHdmwTqmEG8mU9jwi3Ta3LgGMJ7adPGpbjBT0gc5hnuF54bxLpDAloDBomgrFbeFKko0rx1GGA==","signatures":[{"sig":"MEQCIB76HduG9ayb5sea7L8mVyL/ksLUejJm11UaDAxEv2iHAiBR0n5YvyUZacFNs9R3n7YiuCnpM3U1QqPfU8ilPEHSYQ==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":860049},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"2750b2a181cc0293fb0282647a2a7a405f4d08bb","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"10.8.2","description":"On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.1.1_1773624634342_0.8007735145945856","host":"s3://npm-registry-packages-npm-production"}},"0.1.2":{"name":"clawmem","version":"0.1.2","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.1.2","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"7a089981fb4f2f07d24c75a3e6938e410af3f73e","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.1.2.tgz","fileCount":50,"integrity":"sha512-H1I3kSgQtQCzCZaRvg09/UA4D5dmyG8yhZ6PmqrN0jtEMHLFJUtl+stJfu24ylDYK/bliWePSd0GBraImkzosA==","signatures":[{"sig":"MEUCIFKCD7Mm8j/X6CTdgLZswJXlylKhhV6rEwbAXvp5b/8aAiEA/kaEJWLC2Vcs8alcU0Dha+XKiJpVs6z/NsuqgvO13mE=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":861640},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"d952d19046513a66319248f640b570a0038d47db","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"10.8.2","description":"On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.1.2_1773643681861_0.1762909220280875","host":"s3://npm-registry-packages-npm-production"}},"0.1.3":{"name":"clawmem","version":"0.1.3","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.1.3","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"e1dee875da3cf9cb50d4f2a5d62b1a0b1bde1a23","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.1.3.tgz","fileCount":50,"integrity":"sha512-MrGpNm2a7lNVK5p3FW6YsCK/HPt4MHoziu7q4l1DNVmAPYBASUzDTu1zFLDpWzalxE/tqsqwipy3t+e/36rQJg==","signatures":[{"sig":"MEUCIQDIArdsj1aAbHSsNp03dLhwXE/R+Y7lmSg0BVlXGz+hxQIgQAmppbDUiXF0AQ5mRWRA4h7TbFqbc+xOTL30LYcGUxk=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":866698},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"0707ce3b64185a2732b72ee0f4cd3aed618e6952","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"10.8.2","description":"On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.1.3_1773701220188_0.9849477310762966","host":"s3://npm-registry-packages-npm-production"}},"0.1.4":{"name":"clawmem","version":"0.1.4","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.1.4","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"5ef8dd9597722e3c8201fb60dde004fe140d0bcb","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.1.4.tgz","fileCount":50,"integrity":"sha512-iAxZzmOT9BNmaXfFL6c82afZyXFKaIyO+6PFyVd9fkteTw+ssyvmOJzpKp0VEhAMIxT9LqYyApv7Gq368zfUxA==","signatures":[{"sig":"MEYCIQCr6/Vlzg+MKx4AcDtKIb26yocdlkau1bDj8sa7+FWA+QIhAOsb0Ap3OOmbQJXISO7+pPU9QAAPDPKehGUuO0wW7WYM","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":871305},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"5de0e628f06dcd36063d94779ce88655da17214f","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"10.8.2","description":"On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.1.4_1773704746360_0.17812009785731386","host":"s3://npm-registry-packages-npm-production"}},"0.1.5":{"name":"clawmem","version":"0.1.5","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.1.5","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"f9ecb9cc08bb6084e5b758684dc2a198fa863718","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.1.5.tgz","fileCount":50,"integrity":"sha512-w5BIMIOZyuBOM1JzkkTWmeiHVoWwuW9FrplMt92cleF8RbGA1XOUdlsQuD1P+Ci14IUqOVK9v0w8czfkW48ohg==","signatures":[{"sig":"MEUCIQDkE0GYnCyl6ev6dqDaF8Q34Zj0B2IK1Djt+4Qu9AA/XwIgS8LUBVmQZmy8iJw6kex78HhW362WUtbZnP2GQXwujC8=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":871684},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"289e6d1032da69611ed05fd554fab93ed73dcc27","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"10.8.2","description":"On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.1.5_1773706405038_0.7852046220589244","host":"s3://npm-registry-packages-npm-production"}},"0.1.6":{"name":"clawmem","version":"0.1.6","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.1.6","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"f10d4a3299960a258f1ddcae418eb8be2537e6c3","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.1.6.tgz","fileCount":50,"integrity":"sha512-qtmKVvJNHtw6zvjHZHYkMrysQz2wDDsCbXX3lPsGmNG5/SlAlB2SHT8iYJ4AQiNqlMm1DznnIt3wAtwgVfBFpg==","signatures":[{"sig":"MEYCIQCFkMW0OZRE8nl6b+NOia3p2BU34T2h1xgxJdWu1iZ8CwIhALGYaVpv7ckUEcjzDPvA3yHNqdJCwX/LPUro95G1Ykmt","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":872300},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"7a4cbc34922d33d6802ee591293f9e2e4d9f413b","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"10.8.2","description":"On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.1.6_1773728994011_0.6844965910603305","host":"s3://npm-registry-packages-npm-production"}},"0.1.7":{"name":"clawmem","version":"0.1.7","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.1.7","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"f7befb2b6f1951dea26a6463abbcdc1bd1d00425","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.1.7.tgz","fileCount":50,"integrity":"sha512-dvvNSUUPVJWhX39OeBovLckbbNi0PHJXMpEdp5boQCfahT+AqARZFUZuFMO7AdSXj1eZTdjf2BriO/dqrLBHJw==","signatures":[{"sig":"MEUCIQCdNcyi1cmytDbRkl5oy/fSdaaXFrmzrWgetH8CSkeZOQIgLg3i4jao1CfF4WErG//x6xFLydWAoD3232OxVP+c8wA=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":887593},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"d1658554e6211fd6c2fe22fde8b386f8564e547c","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"10.8.2","description":"On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.1.7_1773735027233_0.2604557643162111","host":"s3://npm-registry-packages-npm-production"}},"0.1.8":{"name":"clawmem","version":"0.1.8","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.1.8","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"cfcf6146de7cf33e4118c1abf15207b1ae8ae3ea","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.1.8.tgz","fileCount":50,"integrity":"sha512-U92jQII5WLjxBVOfOseUvTHHGJe5NJGvx4dKabZykCTMQtPopolDItZTPZAwA0QsS0c7GPpDYXwG1MtAvlz3lg==","signatures":[{"sig":"MEUCIC49G6cGdv4O/B3c3Ild5iOk1lZA9MT6zGxd2laTAHsOAiEAogV42W03S9rrhr8rvA7yZBMhKPBbqHq9lztDsvjNrds=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":891135},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"6cc772bf690b1d12a69870f4c2680ff5e93517ec","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"10.8.2","description":"On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.1.8_1774012166481_0.7857159409966952","host":"s3://npm-registry-packages-npm-production"}},"0.2.0":{"name":"clawmem","version":"0.2.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.2.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"75baa50c84495ca6e882aa1cd55bb2640f8ef42a","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.2.0.tgz","fileCount":51,"integrity":"sha512-XfHIJkVnxPY7E6JRMJO3F767dSLP1awjdCMUAwcVL80RDkbfwvo+1p0Rz2upAMJZGicDD+SisK46H6S1H8daLw==","signatures":[{"sig":"MEUCIQCAn3RFjRj/yTEo0OHnQGLee8BFbZdAWQHpsDFBtBGNvQIgCuOxDtmqUpp1JCW9HdJ50o8QtDNTAt8EzOcrtSovsPc=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":952824},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"2cc661c4de2115c0e9afc01afebb146eef13d624","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"10.8.2","description":"On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.2.0_1774291478662_0.12029399514005834","host":"s3://npm-registry-packages-npm-production"}},"0.2.1":{"name":"clawmem","version":"0.2.1","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.2.1","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"a6e70e738ef27ef52de27e2c71e3f6c8958fd162","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.2.1.tgz","fileCount":51,"integrity":"sha512-RmJ1AEKMmc88o6pq6I6GzNPtS1OrjBMudH14Ss/zgWFZ4Hl18xwOtlldSBYixEsXtaCC6e61zn07FJizvusgtw==","signatures":[{"sig":"MEQCIASemqNTCeTb3yPewoFU0GtUtkvRV0go+5LRaq28SL1uAiBIDI5x+r+KVu6pydv9RwsyW/W3FJ3bMj8UFazG5FD87g==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":956445},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"f8c5809523d60d989a650fcf04cfeae95231f8b9","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"10.8.2","description":"On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.2.1_1774294555270_0.42431588329430303","host":"s3://npm-registry-packages-npm-production"}},"0.2.2":{"name":"clawmem","version":"0.2.2","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.2.2","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"2688a87cd87e970c4c059f0f0c548b31d3f40f60","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.2.2.tgz","fileCount":51,"integrity":"sha512-61fIrwBi8vKapniAnaltUsuWz3lWGa6wKcWZQqEPh67SI4zSK0jfWrNiwJhYxR0ulcCleXtzURxyBBYUrFTp3g==","signatures":[{"sig":"MEUCIBk6/AkAURl6YRDBQpCdsZGj76ghJmXSHtJSQolT0OeJAiEAuL7kg8hLQyvvVMDLbe4fM8MlryIG5emf9KNjt8TkLps=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":961803},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"c832951473c4e6e73545cf8736109675c11b348e","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"10.8.2","description":"On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.2.2_1774297190225_0.055474586070841436","host":"s3://npm-registry-packages-npm-production"}},"0.2.3":{"name":"clawmem","version":"0.2.3","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.2.3","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"aef507bd7e548d0a6aeebb14e08d5330e34a9ba7","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.2.3.tgz","fileCount":51,"integrity":"sha512-nl5TlYUyntEcNy1FCPXVzimZVPvdW9nfUUF/ztZpEHLJPqsKUP2x87nIwcKR685oAzBq0cP9OuOpRTIHmzpTJw==","signatures":[{"sig":"MEUCIAgqTSdMt0yn6/8T5o4TOMyzFTa4dOsz1ASFutcrxuBnAiEA8WOF42H6XYx+ipalfLMd0LdwdBn3FoZC5mHhR3sF4yE=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":967676},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"d13f1db3b5011f2b1b76182d83c28f19cda103cf","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"10.8.2","description":"On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.2.3_1774329737919_0.31185886774880034","host":"s3://npm-registry-packages-npm-production"}},"0.2.4":{"name":"clawmem","version":"0.2.4","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.2.4","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"ac5d47995edb15e77c2ea85ebbabc667c755793c","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.2.4.tgz","fileCount":51,"integrity":"sha512-awbZwohzWTe9kil6Hnn1/9qbD0Om1YKiYuYS+uFxsuqdRUJOkPfA4npr7IzJUVXxqwRCUzggE39fibqYqxCQcQ==","signatures":[{"sig":"MEUCIQDahm7qKLQb96L2EToA1CPxnOtuoNpQssHKH3FF8K4BtAIgVHYQvaiOt4PSMmVcbN3vHepEVHz1sPnsl7pkM7t4apI=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":971868},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"a05fad4ede6e74a87e43c15209d17a77bc496096","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"10.8.2","description":"On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.2.4_1774363044041_0.7327847179907268","host":"s3://npm-registry-packages-npm-production"}},"0.2.5":{"name":"clawmem","version":"0.2.5","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.2.5","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"439a1065fd7921b4e2d7c8997fa64e658ec86e6f","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.2.5.tgz","fileCount":51,"integrity":"sha512-MXcwdBkESSDoTew2smyZ329Ci3wzrI+k80T3cQ3mubyKdr2XHimPgTJcXkPxHzcTBb4jkUieyvgCM9j79MIaCQ==","signatures":[{"sig":"MEYCIQCGSJMLYr2BIEHEXN6ACd/kgeAtM6/Azpy09ozgfO6j6gIhAM1yEyVdVdpDbSaHo8FKP43sTEe9QNQ4wjcC7Kh6iCTx","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":972650},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"239e9cecd2d61ca837f649b04f1bed2909fc7b52","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"10.8.2","description":"On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.2.5_1774435770614_0.18335229549580023","host":"s3://npm-registry-packages-npm-production"}},"0.2.6":{"name":"clawmem","version":"0.2.6","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.2.6","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"0acc20fba7b8367280403d28d266550936e3fd5e","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.2.6.tgz","fileCount":51,"integrity":"sha512-YdggLj1j2goetrzc62dvSfzf/OIAGJflSN0T26iS0QMybkLfvm7/eRUEHHJOts949zc5GZ+79YmezyN4lzrcUA==","signatures":[{"sig":"MEUCIQDJrN8TeVkmc4q1BDfyiPQI+pN3xByWFbcYYdjw2y+oeQIgQw9+N8mXJn6bWsd0OX7qFbzVn/cSqB14bTLXmvwliOU=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":978287},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"a1a8ad018554350c119fd135af77d8da52acb164","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"10.8.2","description":"On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.2.6_1774442401595_0.1923582943340454","host":"s3://npm-registry-packages-npm-production"}},"0.2.7":{"name":"clawmem","version":"0.2.7","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.2.7","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"6ff5dfef53874759744d165ee888e5da910b9503","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.2.7.tgz","fileCount":51,"integrity":"sha512-C224MCUHp0D15+krWoQ8cWsdWffr0OgCT+Chm9LElFDJtthRGu21zMRI5F8Rin3+3dE6w6hMqEfvo1QMWzW5Pw==","signatures":[{"sig":"MEUCIQDf0ZPV6POb39mE8tg05suiyIpM7rmpiQ2hG4zkfBnaxAIgISCSq364ri9EHnlGaMy5E+1D7ek8UgWdczQxwxAxIjM=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":978359},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"83172d46b3aa2a1efc6c616ad2d5dca7469b0d3c","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"10.8.2","description":"On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.2.7_1774713126555_0.28798873170359074","host":"s3://npm-registry-packages-npm-production"}},"0.2.8":{"name":"clawmem","version":"0.2.8","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.2.8","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"497c7ca17020965c7279a8e73bdeb51b4d2aa00b","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.2.8.tgz","fileCount":51,"integrity":"sha512-eL0GBwklUeL9MdTs6HHXGhHW+KPczV4GSOb56FgU4KrMa4ZioMWEuX4xW+9PbfxANWgtPIu9c8MyXVYfIMLSRA==","signatures":[{"sig":"MEUCICr2kH/EXlY6n27tcHlEvA+P3gQL21Xu+b8TZNdY7ej7AiEAn9DYav7dYblCp/3WRbv2QqlPqK+hR7fXnzsYOECvX6g=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":979984},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"b61e5217f4489412b370f9032e5c494a6a3dd040","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"10.8.2","description":"On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.2.8_1774881160623_0.19201990563258042","host":"s3://npm-registry-packages-npm-production"}},"0.2.9":{"name":"clawmem","version":"0.2.9","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.2.9","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"cf6d0a65c1612b8cfc508a9013e3c4b2cd83dea4","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.2.9.tgz","fileCount":51,"integrity":"sha512-71/L8P3PxSdZ7F7JJLovDgAys6AiovrLRCMP27NmzEVlQfqHjOCeEZn18hBMvJMseemnjGsbJ1x5J+reW3kjkw==","signatures":[{"sig":"MEUCIQD4PrNtJMJB9tRfF8vZTnN8+lJ21hr/SBCZz9hdV5MIIwIgXfBjSYdzXx62E8COuqrNGdoNc0SDsNLOl4gEIppplR8=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":979984},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"af62042b449baeed81f146bd9219c58ad45919a1","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"10.8.2","description":"On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.2.9_1774946747374_0.7613887024849226","host":"s3://npm-registry-packages-npm-production"}},"0.3.0":{"name":"clawmem","version":"0.3.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.3.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"866385c512439b31c39bdf1eae93fb6d5d73e28f","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.3.0.tgz","fileCount":51,"integrity":"sha512-XbFhBvz1XLuAMgqTFDPT4coOXX6mHnNIWkrYruZTsu5Se7CMcl4zsXIh4YnAgJI8mVzJzcAZHBsCLnuraNnYNw==","signatures":[{"sig":"MEYCIQCrPQWvv3s9Obo9iDpfRnvwmrT3pX7nmrDBgqwNgoiTMQIhAOQpu167PgDKH9JBeOeB0AEOZn+5VLXdVEPqNwM+y/C+","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":981456},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"d66506f13cbd93450915a570a17450e83472ad2a","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"10.8.2","description":"On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.3.0_1774950169893_0.7564891486648215","host":"s3://npm-registry-packages-npm-production"}},"0.3.2":{"name":"clawmem","version":"0.3.2","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.3.2","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"0be9d25950a3f0dc9f1fc835e6354dc803453df3","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.3.2.tgz","fileCount":51,"integrity":"sha512-rgQZhgwhcfW0VhJyo7nwn1t9rGeP5Qw9dqL1Js39G8TT4xOPbvHYDnyd4VpOdb3A1p8Yg5I66wgFJYTRm43wZA==","signatures":[{"sig":"MEYCIQCPq/sK8yQiRPyao8VZijHE574RB6ME+mNpf+Ld1Iu5VQIhAOyFmtDjU2zEHkK758zfFFvUPX2Mm6bWUIrP98hOK41S","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":981816},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"6be7279a68587307bbf7f43f8f8694846817ad5a","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"10.8.2","description":"On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.3.2_1775136094610_0.7285574446631526","host":"s3://npm-registry-packages-npm-production"}},"0.3.3":{"name":"clawmem","version":"0.3.3","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.3.3","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"78471f374f9d0ed4bdd07253d660f695f1254ae0","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.3.3.tgz","fileCount":51,"integrity":"sha512-DzWuZYE285an/BruAUQxU/N4zFqV8V0/M5s471S93o+zwT1mkwRT/K//ZLmB5xz/V06qvSl/t8x9kCiJww6hyw==","signatures":[{"sig":"MEYCIQDC9jYWSCRQjS1mgtozhIgmNO+4iiv24V9lYiV0iAzv1gIhAPs9tVNzWyZhrCQGLYO4gYHlTPrb43LFAxfi/NPz9/Y5","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":984206},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"6c7d741ccb13c4edf888df8b5ef6cb14672acc1d","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"10.8.2","description":"On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.3.3_1775138436309_0.21754150255043436","host":"s3://npm-registry-packages-npm-production"}},"0.3.4":{"name":"clawmem","version":"0.3.4","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.3.4","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"6db4a74b93ab7d26258bcfc91832f94303403bf3","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.3.4.tgz","fileCount":51,"integrity":"sha512-ix6Ex0KgDlMreHDYD3IbDmj8DWd+1ayGoM+F/9e84vXskW8QegKQF7b91a5XtocCNAQ8/I4uSXaxZRwtTCvrDA==","signatures":[{"sig":"MEQCIHd7e776MkFB0vLkakyptwK0Y7/z1ptWzopAFnLEKmhZAiAO3MnyG+727W76lB9iCxmlMpZzianl11dRHuHbmabNSA==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":984542},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"59ecd50811e8232b800a1099aafd59a9e7e642f9","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"10.8.2","description":"On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.3.4_1775140299822_0.7601265327852194","host":"s3://npm-registry-packages-npm-production"}},"0.4.1":{"name":"clawmem","version":"0.4.1","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.4.1","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"4d68c7c2e42d58266d569121664bde26be914c2a","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.4.1.tgz","fileCount":53,"integrity":"sha512-VpxbDISaH+sDKis0xKa+uwTx8ozH0Dzk6qPxy7l+Fa/nJtKcQ0S7QsXkfAiHY9y6lfIhpvW7WBTwHgSTWizDzA==","signatures":[{"sig":"MEQCIE4/cX2km/JsE6tf/kWPRPEFXhXWm8SCk7wmwFWcmiq4AiBYxwJpzCtPyuIFzFUxRahbQV6Du8AJX4Dptq0MGYZoZQ==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":1013907},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"11af463a133ac3ea9490337c9d72ab7aa6128c0b","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"10.8.2","description":"On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.4.1_1775328717509_0.271896266551821","host":"s3://npm-registry-packages-npm-production"}},"0.4.2":{"name":"clawmem","version":"0.4.2","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.4.2","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"f608d9b958f930bde326f6a86bd4b51aba474c5b","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.4.2.tgz","fileCount":53,"integrity":"sha512-1BHE4Hl0bSUDXb3iGIWlQr8cxI4bWwSHnUE0q+I3U/eBZaHlSHRVC7JUK0SPEedyKkAtxicGsUetg3zztcf1xA==","signatures":[{"sig":"MEUCIQCxeBNVYJKddbBqrgaCKPKxC0Bfi1nNaDyRiQKoV9aU6AIgT5fUEkUxyDq9quhmrTq7PYRvf41quyElZjgtKd6Np5M=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":1015789},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"e37e7eb90e1b25d1088ed0e66893e50dd14df0a3","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"10.8.2","description":"On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.4.2_1775330084895_0.39902150993536556","host":"s3://npm-registry-packages-npm-production"}},"0.5.0":{"name":"clawmem","version":"0.5.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.5.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"7b3af92d7c8635a60ecb1e77ef0429e75512c1d6","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.5.0.tgz","fileCount":54,"integrity":"sha512-aT+9Ps7xsJuP365GkWeziWa6MPW4Ou6Wmpmf+7lsb/9Qc4Q6JLou9tU/JcAJWuMvxjmw/EVPUlSosnVQltBIJQ==","signatures":[{"sig":"MEQCIHG8E2juXmZn0I1iL+OjNSLQCvtZRwq0nLToZQhfiP6IAiA8HYYC13uT++VA7y1skNn1XKZmrj1nmIpT+h0YYoZakA==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":1036920},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"133d6ef26069643087a3ae0f5d03f9d68bcc2f97","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"10.8.2","description":"On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.5.0_1775621385053_0.5458393906564396","host":"s3://npm-registry-packages-npm-production"}},"0.5.1":{"name":"clawmem","version":"0.5.1","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.5.1","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"940932c2a82e781e4ab11df46a4f2c949b39d112","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.5.1.tgz","fileCount":54,"integrity":"sha512-P3ibhrl6+l4XPMxjL0FxD5t2vou+i+K1PjtZ8+CPd3rLlHKhZllqVXVi7LLL0IHpT6P6ZjaAV9UChAtABK0brA==","signatures":[{"sig":"MEUCIAcs9hAK3ELphv3JTwZh+22feVXL9bUQuVAbejE7q9woAiEA6MFmepLWsUP0oTeS6VU+De4ZxCs0EfM9Bu4qxmbb9QI=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":1069471},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"c7de631220c6aa0a76d3a43b2c817e43e32942f1","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"10.8.2","description":"On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.5.1_1775628177092_0.1599833508737185","host":"s3://npm-registry-packages-npm-production"}},"0.6.0":{"name":"clawmem","version":"0.6.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.6.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"fe8e00751e3af8c0e7c68bb8deb15b60659e418e","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.6.0.tgz","fileCount":54,"integrity":"sha512-w34SObxLmxtNoxdN/w+JttTdsedHmmk0mU8u0NBKv+wMivc93UcmWX/l+cz9PCqXjEiOxbBPS+EYbVTFtXl+Ww==","signatures":[{"sig":"MEQCIHyLHBzp9U6Qnd5o786YaApljEJdK5abn7LIIes512nAAiBR1Y3eYcj+m72yDmuYkWOMwIks0CR4C9TaDJBfnl7Gng==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":1085566},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"2d6c76421bc57deebd5d4a08097532ebdbac88bc","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"10.8.2","description":"On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.6.0_1775635141067_0.3419452988322256","host":"s3://npm-registry-packages-npm-production"}},"0.7.0":{"name":"clawmem","version":"0.7.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.7.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"636bf5538969bff0858f897a8ea75e3e81bbfc98","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.7.0.tgz","fileCount":56,"integrity":"sha512-zI9NG0E7mMfcEQxLt6+2jGPmJCMuK9A29ih9KD8Dg9RFdAVFArbU0X6fzXfbbHYLiDoS6yiVIOdLSIjajRaIDg==","signatures":[{"sig":"MEUCIQDooSJ5ABS5kH/z4pmz59lJ+q6/8imFkBkk4dud0x8kcgIgLyWU0FHctSQL6N6ux0Sv1RNY3DWnoTw4ru6Ggskv55E=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":1115704},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"22a316516b705e93552d857ab3f53d8145a1d676","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"10.8.2","description":"On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.7.0_1775645984045_0.04894158494088341","host":"s3://npm-registry-packages-npm-production"}},"0.7.1":{"name":"clawmem","version":"0.7.1","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.7.1","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"d479a1c385b46e1bee3a1b023b74bdb7c3fa6cea","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.7.1.tgz","fileCount":59,"integrity":"sha512-ZLOyMEQI+aePNjSLB/JPYfGAqJfKofQNaGHz8Et0Addk/nekqqCsSTrTnbX0SBKNXZWfMac1X3RKo7EveHDkGw==","signatures":[{"sig":"MEUCIQDwX7YYpboihyySk8qzq/zbCFqZmCgYCfVrs4J9DQeb0wIgX56n8s1N0k83tG8ZVOihVi4S2At7qNhoimE+LfL9YCc=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":1192134},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"e1279a77675e0e314a28f9538bccf51035ca394c","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.7.1_1775764743591_0.023638775160828684","host":"s3://npm-registry-packages-npm-production"}},"0.7.2":{"name":"clawmem","version":"0.7.2","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.7.2","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"7105f19705f6cfdb881ff7e4300c5c736b49d90b","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.7.2.tgz","fileCount":60,"integrity":"sha512-3cmV7rFFrAGru9e93qs8P64m+bKl/KYYwMY6HkVJqNiKczxkPXmG4k04XlEnZuB1ceaZxD5NSxMmCzdnvJuveA==","signatures":[{"sig":"MEYCIQDqHtqo9kcLJgLpn8Xy0xflmihJkjjD9vY878Ec3/VyOgIhAM8EVq276h9Nz5mcxJFYWxsRVUz8eP0ehYKwWi7PQGwU","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":1222780},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"2fb1b04d9e5740a7c13318b24ca3d74489f11583","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.7.2_1775769299208_0.5025567828718682","host":"s3://npm-registry-packages-npm-production"}},"0.8.0":{"name":"clawmem","version":"0.8.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.8.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"67543128d9d2e03104534ae37b29802ee9a469a7","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.8.0.tgz","fileCount":62,"integrity":"sha512-REsaRud/zHFHwFpfBqE1GhXpEGNteSjbOEFQbf2vN1x4ch0CISJec+kXqXVHtrymnY9qQudk+yFTNiCMlaw66A==","signatures":[{"sig":"MEUCIQD9TXbwoUoNuIxR0JC+LQbB4efrFE4tPvzw85Xf0mG2tAIgPt/QhlHVUurEysmot0zyQ1+JlnDD4bsBFeQLsYAQXGU=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":1266644},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"1a8c84490c1c4f593ad6fbad430c21f46e955811","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.8.0_1775772707778_0.680165435943308","host":"s3://npm-registry-packages-npm-production"}},"0.8.1":{"name":"clawmem","version":"0.8.1","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.8.1","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"640d0d2a6f37a595a6015066d70a4d9416901103","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.8.1.tgz","fileCount":62,"integrity":"sha512-3sPkod+WY8nsuDKb4hh4Bjt1h/2mgRPCF+Pygpzss5eCsue18yL2YC9poZRGqveijoloZW62311CpfoNxDmEBw==","signatures":[{"sig":"MEUCIFTmE/oL7pH1OlvqLucRn7wLduPKajwF262Pm+w9yWULAiEA7Uumals9aHqLiBhJtE6Yz8f3nUqeglAJxWrLAI+3lIg=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":1280831},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"a85e86d69145aef6ed44f92b392d4284ee2630f9","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.8.1_1775775151832_0.9907692832497563","host":"s3://npm-registry-packages-npm-production"}},"0.8.2":{"name":"clawmem","version":"0.8.2","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.8.2","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"6ddf15bf8038cf874f85113a67df88a1d18c5ddb","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.8.2.tgz","fileCount":62,"integrity":"sha512-90qqcrK9z3Sw0KiearR9FDmfQKg1+iSkEu6j/9/3bF6fWRy3j34vtbP2o1QCOzPSunJJ7KtKeBgc7qUfD/nP6Q==","signatures":[{"sig":"MEYCIQDCVQ6DMKDkzX5zLW4wzCAXJyz6q/UjQsxkRUEk7vVNrgIhALGSI+orjXJnfpvDL/N/niWG0rPxLMkgaIncnhBdU4K6","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":1298806},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"c5c20fc1d297e439c49677866b27757cfa893d4c","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.8.2_1775783747308_0.11599822329289533","host":"s3://npm-registry-packages-npm-production"}},"0.8.3":{"name":"clawmem","version":"0.8.3","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.8.3","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"955b1cea12892d9a1926c90045ecda62cf481f20","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.8.3.tgz","fileCount":62,"integrity":"sha512-G7G46QaNBxyJPgk4Hv0BxNMdm1j/w0q6k1adWFHxA72D72NO9Qei691nk9sK0E4I5uMi/pV9xTLRpXnJrhzF+w==","signatures":[{"sig":"MEUCIQCC0993xkqbPicT6a8ZEZngFl55yxpfW2CshsGMFmBZOgIgMnuLq8eEGOqVPcmnzGYKIoUCJpNxPqj6L9lh/s26XWY=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":1286204},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"cf3b68f820f1c41555edf3c143db2868018f3619","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.8.3_1775793742835_0.07717015257687998","host":"s3://npm-registry-packages-npm-production"}},"0.8.4":{"name":"clawmem","version":"0.8.4","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.8.4","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"992de0f048a50e8e2b393058519e260e2c6e56b8","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.8.4.tgz","fileCount":62,"integrity":"sha512-erQC1mVsACL/DbMrv6oW8vsM0rV1Rg6PNCcKHka9h11TML88jtIJnVY6t5LPTH2XFPcPk3uAzN0FeofRDyah1Q==","signatures":[{"sig":"MEYCIQDCU7uOg5goe+qcj3LJ/TuwFPRIqYWxbo9AbiGYgRpyRgIhAPhpmtVCnlB1Sgqn0pv0A2W3KCZgALjUbMHSu07wAFJG","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":1290231},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"06712b6cc7547e78bf21ac29be020f3dde158df5","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.8.4_1775917683957_0.21512992902940087","host":"s3://npm-registry-packages-npm-production"}},"0.8.5":{"name":"clawmem","version":"0.8.5","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.8.5","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"76e797e4777532ae4b3342048644dd903ff87e49","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.8.5.tgz","fileCount":62,"integrity":"sha512-0yOGJOSVM4JRTEMVUvrmS9MAExj50iXxqfs6vsO/dzU+qEY3ZhdnOwqmo9xEDxd7h57S1zjElMwb+zGQLwdjyQ==","signatures":[{"sig":"MEUCIH4ZtDLw6CRE//iaA79/pJ+EkjYEBpvYBUVrOl1Tyv7HAiEAtdCOnqRlF3nwnCamXLjheHnsd4CwAbfjb0Y6cZ0OYdY=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":1301567},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"f1272e2bde5c3a52767a4e06343dad23b2a23870","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.8.5_1776039169539_0.3480176159234152","host":"s3://npm-registry-packages-npm-production"}},"0.9.0":{"name":"clawmem","version":"0.9.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.9.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"73e8521e3d9c9456c5158056ba5d21b1bcedd432","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.9.0.tgz","fileCount":64,"integrity":"sha512-w0VEsu+MdbYET26CIdZPvb0UiD71VEdJ4LvG6/QFFFoWfLEnU/Qacrd0+MCTP1Ok6QnILA0mN697YKD3qBw/wg==","signatures":[{"sig":"MEYCIQDwxdn5bbwdLTevqCXsLX92o7b72CDEI7e0TxvcKZa8nwIhALdlka7gn9tZqzBIPvzNSkjE/AihRDCrFPlmmg9fzv1n","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":1344586},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"cd594f9da88204edbd74bb1d15270ddeb6ebe096","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device context engine and memory for AI agents. Claude Code and OpenClaw. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.9.0_1776053351515_0.1192136698982873","host":"s3://npm-registry-packages-npm-production"}},"0.10.0":{"name":"clawmem","version":"0.10.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.10.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"9cd39efc9bf7d220219ba78b373d32b4582b7659","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.10.0.tgz","fileCount":68,"integrity":"sha512-FrWHiKfKjOx67WmdM8PUDNZQU+bArX2w3Dak/yrkJKD/gPcX9zI/8F+5zyVYBfBZInKXxwR5nuI0ECJXEJbFbA==","signatures":[{"sig":"MEUCIAwHzfJEhgC/fMDgkeJ4d3H+JgeOqVnHjsC2GFb0wHYSAiEAgqBBD7NJaTvTPRbUPp6OOI9vQxaIrA+zAAtJ+NlkhPI=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":1397731},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"85f2a8a760822e04a9f3d28422602309f6f62e2b","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.10.0_1776088081797_0.6709579464510438","host":"s3://npm-registry-packages-npm-production"}},"0.10.1":{"name":"clawmem","version":"0.10.1","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.10.1","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"d306a7f0950d7aa38e2bd5c344aaf7a2b5c5bb79","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.10.1.tgz","fileCount":68,"integrity":"sha512-s2JpvtyVwLalNXF0IeNzWacTeN/nAPROEh2ZpC/ksA8s/JLfGsunMHNFjxh9JiveCGTGDpUXK3C9O8HSoYITug==","signatures":[{"sig":"MEUCIH9SHxic2I6+7V0KbTa6xAVRyl4QY99d6LAWjHBGwDrmAiEAudibQMxOj1AeHKFASQFam1EoJxe4Sh/hzZUlHT3mhfw=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":1405556},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"9a793b2ce52962e8e7d0b4d5c61c2d8eb4ebee48","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.10.1_1776571576306_0.7417394874766368","host":"s3://npm-registry-packages-npm-production"}},"0.10.2":{"name":"clawmem","version":"0.10.2","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.10.2","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"6738372f0b379d871b9ff1e05aad8b91e6174735","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.10.2.tgz","fileCount":68,"integrity":"sha512-b35P4kmWUu05up+QP4a9f8aOBczPKm1fdhUJWddIYevDRyNfNnyaSpjJf8m5ImffNATKiUb2E1iepB6HiMrXlg==","signatures":[{"sig":"MEYCIQDNddDk5CMaylDA81mXqLvMvb+glo0+DI8nugqj5nbgNwIhAOyMYt5X81cV+5FUTAi2Mtzy1V2+GQTxnCeXkX8Dgq2q","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":1411158},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"a74b7ed58c214d2db07251647d61785cf4b1adcd","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.10.2_1777380110329_0.30755295674356264","host":"s3://npm-registry-packages-npm-production"}},"0.10.3":{"name":"clawmem","version":"0.10.3","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.10.3","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"1f073124406149d948ab537a4c135214a2042434","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.10.3.tgz","fileCount":68,"integrity":"sha512-whCqnFai7lcaSFUbadg9ZXAFBY5TxD/gXP+HOBcS1QH/IrLXRlbIbKxW/bHYPsM+WITvknaSOaZn2j5wm28/Jw==","signatures":[{"sig":"MEQCIE12VQAAFPKN1/rYKgc4bn9NZ/DquixT4J62EFwcC9zJAiAIJcxX5rJOB3PG4L0IemZS09hQZZom0vHCHJUqdnu3ZQ==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":1425464},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"05e49e1037a4218032b182ff233e2fda5e3b3abe","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.10.3_1777891742785_0.7120979745316196","host":"s3://npm-registry-packages-npm-production"}},"0.10.4":{"name":"clawmem","version":"0.10.4","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.10.4","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"d46900d1c69851e2b0aeeb25207d6497d00993c9","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.10.4.tgz","fileCount":69,"integrity":"sha512-/kQC4ZxWFTUZrR5lvu7jqAVuQjhpHQLZ/vap9m81L2BcjmIAAuDpX/IgYbZX/MAUmSXFAYt+kf/UiQm5dfld8Q==","signatures":[{"sig":"MEQCIC1YcOQom3R7KalscFlh1Y02F2n1D6LG/ixNRNaO2Y1bAiAfdei2EkCd9kLsTFe2eC9zoQCTNa9gYHoY7M9No2s1rA==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":1446658},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"b0241190e8018575e9d2dc7d32bfd17c44218839","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.10.4_1778235908093_0.7741260889230586","host":"s3://npm-registry-packages-npm-production"}},"0.10.5":{"name":"clawmem","version":"0.10.5","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.10.5","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"65277c6f85360fbe95e0ee9f6990c3571b0f3539","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.10.5.tgz","fileCount":69,"integrity":"sha512-hxqa70OXKP3fNbUrVzCIeIkr58ekNrW0AdKbnGOJ9O6fdnI6WBxcUF4As5mFHlIQuRbaczW1vcS8t20i0kS1pA==","signatures":[{"sig":"MEUCIEJSkQ8S2VihogjgZFTLko3xiKYpFEgWcyh+45FlERGcAiEA2L3yZhj/EX87HlITUiI5cC2yuYp1oxbmzoWvLcAw4KA=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":1447644},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"8aa1068bcd75fb604bb134fcc36551488a8343d1","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.10.5_1778839421709_0.996166237408592","host":"s3://npm-registry-packages-npm-production"}},"0.10.6":{"name":"clawmem","version":"0.10.6","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.10.6","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"5e2d085330e0107ef6eb3724cce5435daaf75dc5","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.10.6.tgz","fileCount":69,"integrity":"sha512-P6t7sCR67OOOSZF5JKLWl38YRp1Ba5fIe3/rn5rmq89eu4J/F0s4MXcNpZbz4qgtMKI0H5ITdB/8AHkWVODP+Q==","signatures":[{"sig":"MEQCIB8kPtL5AkjbVIaqmCtvyY3VMDIaQkJeWnhl4lbRsev7AiB7WTwgCF65zzdmrJDvciGWnZA0mC/J2loIGWY5gIfxhQ==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":1455268},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"7658f3cd292604d7d12c553ff69599e1fcc8c83a","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.10.6_1779289905273_0.1872792023769405","host":"s3://npm-registry-packages-npm-production"}},"0.10.7":{"name":"clawmem","version":"0.10.7","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.10.7","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"55aefac2612e1de97d916c051422563300b021e7","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.10.7.tgz","fileCount":70,"integrity":"sha512-IrZXSSvYVh/NYUl7M68065s/klNiq7Bbdk05BbQ+39X4DB8SxTgCPV2+ez/ggLwKNG4vKjt8qFOiI/zzYERqFw==","signatures":[{"sig":"MEUCICgagpvjDtAJbbvN1rvWnfzgaTQppezJsm44D+HVbU5mAiEA/qXNmU1O1uog7ZK/tU4eKc40hxYrAP9rFnIUQDb38H4=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":1488207},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"8016a442b1b27af64f4a5912016dd2110aba8b89","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.10.7_1779305325515_0.6386272790806622","host":"s3://npm-registry-packages-npm-production"}},"0.11.0":{"name":"clawmem","version":"0.11.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.11.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"93e7b25425db8e55d78f5f9a77b42a513d3a31dd","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.11.0.tgz","fileCount":69,"integrity":"sha512-HUC/PL3Zb77TAnre2+Zbcjius5W5MolZOBeAmvonEgqlhiZ+FM9jzMu41XEMmknBDIg8X2BK39qgpi7hPfjfeg==","signatures":[{"sig":"MEUCIApfjiyNeIhOnHq9j2s1TEv5z0+1iLVq2xjFEY3+UxcyAiEAlHqUOBoURfus11MOlm7gkxvlOb765uwfnC9Q4kkvLy4=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":1481652},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"9486a41a9649be6f36e52ccd1228957b87b31ec8","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.11.0_1782160852790_0.16603563668950927","host":"s3://npm-registry-packages-npm-production"}},"0.11.2":{"name":"clawmem","version":"0.11.2","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.11.2","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"e87e6f2ba696b0b20e53000cee298b70cdd14025","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.11.2.tgz","fileCount":69,"integrity":"sha512-NjCPIKbHRj7PBe2Bq8owv5pzDauFdoHXuY/Tu9DmJDiXKuUBY9w70RV9YfqtHsz96nGHfVwceEB027AaQ2pjTw==","signatures":[{"sig":"MEUCIQC+tUD1JFQxRM4+bDT0Wyfa2ldiqICvA8hBlbV/2lOwgwIgcG1SOzj2ciYkvRPzN9hXyZEGv0LdaJa7nG4gu0JCanc=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":1490243},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"bf0e6f07c82284b3489608c37b017c4feb552af7","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.11.2_1782244959467_0.20750085314217892","host":"s3://npm-registry-packages-npm-production"}},"0.11.3":{"name":"clawmem","version":"0.11.3","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.11.3","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"5381fac2abd56c3008f4ee84eab9d8652f85b6d2","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.11.3.tgz","fileCount":75,"integrity":"sha512-zI1tYKjN+BLHmJu1+2nzFjJWz38t0vBW5QA/ksw1d6y+Ybe6MaWVfpCzoolxEUSWQWar3pffnUINf0ueYUC8ow==","signatures":[{"sig":"MEQCIELJyl2Q+yrsDKt7p7zbJrh1hwPkvSfI/aYmdgACxMdQAiAcGrPltS9vCV+WqfOd3PDb/oM27KOqMzThlLxma7/JYA==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":1518115},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"01b21f2620bdc82b1c61b9a5fadf2135a13a3015","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.11.3_1782322026354_0.22752761532367005","host":"s3://npm-registry-packages-npm-production"}},"0.12.0":{"name":"clawmem","version":"0.12.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.12.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"cff2339d675845f054120f14d4f860beba341643","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.12.0.tgz","fileCount":75,"integrity":"sha512-nSdwuPrC4/89cb50hotZkHKA8Tdoim+l7tZWkOLCHP1yTu2K6qaV18/mbtUOIkRn1r24Ph2NNG9o+pxpUwZICg==","signatures":[{"sig":"MEQCIAXPvs9x3rRHbdrbC259RplXxjDh7ksFvjgWipHZVccGAiA0q6RDUsqeNWxgEmawWcQ8GdWhw7/Q7AEBrn74TUdkCQ==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":1521234},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"5c7892bfde5a8fecc1373e62d7dd2997fbe6966e","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.12.0_1782379426808_0.5220554067372376","host":"s3://npm-registry-packages-npm-production"}},"0.13.0":{"name":"clawmem","version":"0.13.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.13.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"dc191a869e63e6d73102a1a1d15083a72be148b3","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.13.0.tgz","fileCount":75,"integrity":"sha512-l/WOj4lIaoDDXC1ReJ3lpxfEr5eOHyiSGVSSJwsdwvVDI34CvVX4nIOhXo9uhzScc7/DggUaQch8FYEatE0BGA==","signatures":[{"sig":"MEUCIQDNrVdDitZQlcjBUDE7ZFoLV31Sonl0fkazIM2enIGZiwIgIVYsPojUVMcRf8r/99v/nxqwMDn07VoGE7+tV5/8tTE=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":1524214},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"ad9c2e4186514a022be9e6749c31d472d8dcb3ad","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.13.0_1782398363845_0.5294614902692825","host":"s3://npm-registry-packages-npm-production"}},"0.14.0":{"name":"clawmem","version":"0.14.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.14.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"57c955b1b3dc2bcd04068ae0ead8774cad83d667","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.14.0.tgz","fileCount":77,"integrity":"sha512-unfNRQlVaNQ3oYgZJtbSb5KHGZLGVjtEoPAPmnCE3Bv2yMGJBVlpcu8I4/jxSOBb5zc0DbxNcBLTk+X7qBxmrw==","signatures":[{"sig":"MEQCIAUOiN45zVx/CaUeKdFBJrJg5uo/pTLR9jxxpAoB6h3EAiABx4UqXNeZvLno1pE60bFzX/x3nSrruiyhy3VggYmqyA==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":1553222},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"ec6d5a0eab619e73792cc56af05952f9d093dbde","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.14.0_1782417585410_0.9946871725206463","host":"s3://npm-registry-packages-npm-production"}},"0.15.0":{"name":"clawmem","version":"0.15.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.15.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"a4b77c7c05ddec6edd480f105ef59e5a4576e1d6","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.15.0.tgz","fileCount":105,"integrity":"sha512-6jDf7GtEmeF8NLYlGaVZVkgvzqkl+O/0FPsn3Yst5kfsi5blOPEFcUXwhVEMbAHCx3Bufe0lRpnvvfBB6HFzzQ==","signatures":[{"sig":"MEUCIGAC//b3o3Xuh2NOpERs3Jt4QXtHwYZo7RwC7oNEsB+BAiEAjJbdyvNOw6xhPcNsxOQzAzzSTo/NCjfBTsAH+M5mo/I=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":2370415},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"f62830e2292b4bc63347c6a352e6a9c5fc7f8550","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.15.0_1782824909254_0.04511451091808483","host":"s3://npm-registry-packages-npm-production"}},"0.15.1":{"name":"clawmem","version":"0.15.1","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.15.1","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"0ac7a9e069faf0febd8b2ed9d9d13f8e732f61fb","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.15.1.tgz","fileCount":105,"integrity":"sha512-1faj93Q1UtOlkd014Zh3ncSMbi9y6t69ItHzQg7HZb11VZ3wYt/WbE5ECbi+tX+axTjjHrwsYZltMY/gEpRs7A==","signatures":[{"sig":"MEYCIQDNi1IMfiA16bZTEOCC44VaFQCrSJBuU0RzogxoU8mu/gIhAPBkGcspHSVFNnqoxGdyx+FugSIzneH3b0dZf0mctWwI","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":2374644},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"8fa0ef0d7ee99032ba11609ea659e542ca7829f5","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.15.1_1782832599377_0.6451593692483992","host":"s3://npm-registry-packages-npm-production"}},"0.16.0":{"name":"clawmem","version":"0.16.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.16.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"877fe6f3bb732a5dca77ea103ac75494c747be20","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.16.0.tgz","fileCount":105,"integrity":"sha512-9rGLtRrHVGcgCas1Ije5ouJ1+nkWBUXdDitxB2fjflXIQzmendvLIEZ0LwxZH9WE/1HIbYa4iqLRV+LNhSFn/w==","signatures":[{"sig":"MEUCIQC29KgdJWFrzQ2qYmoZq7Ul6mknf/YVJXZPyJ1VQeRexwIgL4M7NKdDe5uXWJc4yX6C8CnY5n2+H+eMGloR4OgOCfc=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":2380121},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"1d42d7f22377fd576ecdbca3eaa41a99dbfc8f41","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.16.0_1782921821680_0.20126277492783773","host":"s3://npm-registry-packages-npm-production"}},"0.17.0":{"name":"clawmem","version":"0.17.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.17.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"ec11794580661a12b23991396cee77eb779bebdc","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.17.0.tgz","fileCount":105,"integrity":"sha512-ViNyw79E1sKsqdmr9MCZuFb84D73XRqvOcH1TOsJMsrVANFZuHROV9iH9W/9DjGUv6QmHuyDDdMtqp+dCDw5Qg==","signatures":[{"sig":"MEUCIQCQ+NLrSjNXnGVPu/DjX+JTLIw7f+yAoyS9aS/E6M6ZqgIgIdfP/mniNATBizYanDlBBeE502Ni1TFwXMtei1XMDt8=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":2391186},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"862dbd0590649f431e4748d32e1a1eaf7a0772ad","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.17.0_1782937343068_0.7179245050487346","host":"s3://npm-registry-packages-npm-production"}},"0.18.0":{"name":"clawmem","version":"0.18.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.18.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"b2df88070864ee1076b33bb0767bda2e25ab2bba","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.18.0.tgz","fileCount":106,"integrity":"sha512-F4JvMCbqw8B9MbsIFKkGsux3ygREGDArShZJAI0ryTRAaOsS/8E05U+s5j6tCH/Gkp4T9u+OhT8G3hyqqctH4w==","signatures":[{"sig":"MEUCIQD1SnA3r1HoFGA9RD7sd6MCk2yoOy+JL8QNitDGoA1hFQIgCwQi45udEPKjhl1bAIR9hYn82lJbJqJkd8+PSFLVz0U=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":2403008},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"9ef9b97ec6ebfd9c42353569fedb807996c46688","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.18.0_1783181933973_0.4987327365397407","host":"s3://npm-registry-packages-npm-production"}},"0.19.0":{"name":"clawmem","version":"0.19.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.19.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"4a29014f0f5c8a7911b25de33c0cd3c44ba9fbd6","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.19.0.tgz","fileCount":106,"integrity":"sha512-JVH3eoqeCP29dUmymnMMvfXZ7gayYe+2iORm921ihdheCOeMULrLwNyclEQTOJndp8hid4keGp33i3lZrTppnw==","signatures":[{"sig":"MEUCIQCY5sbvW6vepo5o9nfd+kDBzaQny8lAKUb3fmjk8JmsGgIgFnk6VPp9ikmtyX7092r8K4PsS4uU2mudKZC9l1fznL0=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":2406606},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"78b6e9d58061b94757f5bb4a260505bc20cb1706","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.19.0_1783193986604_0.16518537144028","host":"s3://npm-registry-packages-npm-production"}},"0.20.0":{"name":"clawmem","version":"0.20.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.20.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"4d155521ad7ca4a07c11f337106c3d4c0a7dfd1c","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.20.0.tgz","fileCount":107,"integrity":"sha512-NArpqwwwMFXrrD6TP0a1tFQEkdSqDsbxAkIwBXFcbkwhjAdkUEAExXbr8dQxRsBNf4vHPsDIb5sG3gy98XcPGg==","signatures":[{"sig":"MEQCIFeecGITGv3VP4Gb7B2tkfSkJpJeeOJ3ytUJZFciRCRLAiBJWzB0ZZb5cuqZ5wskbRZNFaIDsOOBsStBy32RsCp0JQ==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":2427544},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"6783146b3c12fe96aba2a193d6347fd59e22870b","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.20.0_1783262711858_0.3410669064903489","host":"s3://npm-registry-packages-npm-production"}},"0.20.2":{"name":"clawmem","version":"0.20.2","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.20.2","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"46867f7d094c23ca637eb644bfe37c9f7423b055","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.20.2.tgz","fileCount":107,"integrity":"sha512-BtDF/i6WiRykWAHZa9S0W11LoJc/EUXZ2qsIAt4WfGI13Z4wEn8bNGrvd6i0+Vz5IStjRLDUSYKBF+prSHq6Hg==","signatures":[{"sig":"MEUCIHZt2lNOX3xiPzT0dieU0W0CQipMQMOuM8TmNWgl+9CcAiEA2qcxrNr0cL4YXu1OeL8vpP2gI6bhYwzx0x+71o6D3hs=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":2428312},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"82c81c43dcbc3a2d5baa82353ad8089111448bbc","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.20.2_1783414415156_0.39385773292303616","host":"s3://npm-registry-packages-npm-production"}},"0.21.0":{"name":"clawmem","version":"0.21.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.21.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"417c2d26ddb7b055cc383ebb86335ae9a6c85c34","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.21.0.tgz","fileCount":109,"integrity":"sha512-2OjChPxw66OKDCVU+VUvc5op2nSeX7Ajpqcnt9R6bVNY13vodgqngmv+4niZR5IucwB9YVSZgBnX5q6sWT735A==","signatures":[{"sig":"MEQCIEUHlh02/WF08Ylw5mRH/JLCwrad567EHr5NYGME27DlAiBERNJy+M+RGh3Qix0CiAq6C2cITvD5y9LiqebLXNxP1A==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":2505171},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"7bcfc5a09c6b6b479f8a1b1ffbb76f3d4e1f8181","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.21.0_1783667494316_0.5909899246086594","host":"s3://npm-registry-packages-npm-production"}},"0.22.0":{"name":"clawmem","version":"0.22.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.22.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"4b8de1b1c6a0d0e20ddb38e41cd343efe9ac2370","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.22.0.tgz","fileCount":110,"integrity":"sha512-wB6xvzLDMamMsOAk/EaD7XVTAJQFX7P7m0upeltXKX+b9DwbCmjXPA7sxOLEXNMrLVjLAy/INmSM+V19Q/VLcQ==","signatures":[{"sig":"MEUCIQC8B7RoE1P7nHjIWBL0KlO5du5GJQSLTGmjXdZy+jwYAwIgMFrV0GOiEOp9fYGTK/RvcJ9GTQ3eFhhJoIRLSPeWP5s=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":2517828},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"96efe3580341c4db45fa796d27ebe8d4115d6dad","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.22.0_1783678032921_0.8210212874349763","host":"s3://npm-registry-packages-npm-production"}},"0.23.0":{"name":"clawmem","version":"0.23.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.23.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"85521011e22d91a9cc2cfce76b8d48e6f09346bc","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.23.0.tgz","fileCount":110,"integrity":"sha512-G244tHVbZhTqvKXjviXoXAcQ9g4VjPkZEsgGFfLRqj8BB7WdRDIOdLtjO4zO4rtr+zMkyRQ2ICIrbrum6r7AuA==","signatures":[{"sig":"MEUCIQCzseIGOVYqAwZQ84Va2tRiV6yD5cU41DIk3Qy+cSF2+QIgFOw1TrNJ2L+H9xkTuNDAJCpdIvCXbe2R57NHnFv0VpM=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":2524316},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"e9205ac295132980115900f5f0fb9220651b9403","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.23.0_1783683075185_0.6965824691193421","host":"s3://npm-registry-packages-npm-production"}},"0.24.0":{"name":"clawmem","version":"0.24.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.24.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"5c724e94a34e555a4dbf9865c54681494206037a","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.24.0.tgz","fileCount":110,"integrity":"sha512-3yIu70BFfjBfUNVmoFrHn50ALd/IJrOpyOWxLQKmrQHtBqYB1uNZpGX7bT/DWUx/GWJBdVAP7H2iK/yE7wJJAw==","signatures":[{"sig":"MEYCIQC7li3OZ2ze9MsP70eap83G1Qm24a8vqaIacaISiGX9SwIhAL4t6d+z6wnWLPn8NDdLZRLO8qPDqQd3yZSDcfjW/UfU","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":2530632},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"580f3cbb8ae6dff3e0f8faa7abba371efd928079","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.24.0_1783698600966_0.824810046620803","host":"s3://npm-registry-packages-npm-production"}},"0.25.0":{"name":"clawmem","version":"0.25.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.25.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"5dfeed9be76efcb6dd2a1ccdb521578a90c22c00","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.25.0.tgz","fileCount":111,"integrity":"sha512-/JFBH14Nd712FU79yusJHj+v0o29VbxGCSTIgLeQHQWYRWj/YUHZ9aMMJ+2MAvs3/sX7mKOaz7C3Pgh1Dbfduw==","signatures":[{"sig":"MEQCIDGxyfOxLE9hbHhEJj4m81iU8yJptNtqwKnpQB5/wV6DAiBCCrJZSsa6gxTomUo2Loj+pGtke1Yj7f3EH6NfwB+j2Q==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":2544226},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"bc6589c1eb4e83854f052295b2df79331f67d745","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.25.0_1784349565093_0.053383339813718456","host":"s3://npm-registry-packages-npm-production"}},"0.26.0":{"name":"clawmem","version":"0.26.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.26.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"f7b12a288e6ca9cb40a129cd57466092ed22de2d","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.26.0.tgz","fileCount":118,"integrity":"sha512-ht1Rql9dclpVdHMexYdjwgaAcryS7tRYRGiXS8tIIrdpCIvLzrKxGR24Y19e1j46278frFaXiV5PLMzln2p/4w==","signatures":[{"sig":"MEUCIQCBn2q6SHoDDVROQ6U55Q90nFt5EZlPnv/kAXqnO7YbuAIgaBJV+nj9/B7D38qLKPwm+ah1WSRvPYhyvzTayd4GtAc=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":2590055},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"6c51d525e9d0e3e11d9f1552054af205838ae4b6","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.26.0_1784354783939_0.9476719915035794","host":"s3://npm-registry-packages-npm-production"}},"0.27.0":{"name":"clawmem","version":"0.27.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.27.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"4a6ac042902839361a3a8826bb458b5988b76ab9","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.27.0.tgz","fileCount":118,"integrity":"sha512-qLJwLu7cH04NFtOeaXRknYazIfOkyUHfAdbHlG5N+cTO1D1QDr/I3of2OwAgcTM7efF+uq+1FHiQLXmy9tzAQQ==","signatures":[{"sig":"MEYCIQC3e04vv9ZIDYlSGFtpAMvWDYBK6EGkCtLSmEMf+fGSoAIhAJ4REAz18OR2KQHB8SRcjkXdFmQ2GaPSFc0eQrNRlB+b","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":2622383},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"93bd05ba1f4d53afedb22a9e6e12159d5e810f97","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.27.0_1784363463492_0.939848676464859","host":"s3://npm-registry-packages-npm-production"}},"0.28.0":{"name":"clawmem","version":"0.28.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.28.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"b5513304cbe4c2cc1aa71d14e330f107805b662c","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.28.0.tgz","fileCount":119,"integrity":"sha512-+W6iOJ2cXi5CIWDR+es1P4QIwVAiyb+zneTSjwXxdmNwZBr7CVOXIW78l7r+bPn/8eLggn4h8jpDgkUohBrOcw==","signatures":[{"sig":"MEUCIBgbQeQ/J93EoMt4s1+N2TLqPUkn47Y9ITUprrscbWxfAiEAyUgpEICmDjvhqZzIEd95POBqPDgoluPF9FXfEWsGDnM=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":2689237},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"41fd12153e23491921673cfe11aab017b8151078","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.28.0_1784478044570_0.5854094417089466","host":"s3://npm-registry-packages-npm-production"}},"0.29.0":{"name":"clawmem","version":"0.29.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.29.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"752b68d34e396cbeaad74fedf8084f618a0c90d5","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.29.0.tgz","fileCount":121,"integrity":"sha512-tJsdz1B8h1y1YpBEpVEklWeMn8oy/9h90ZnPSVIMW/9MoWYBMcxqfYXh9TD7motYNVYtOPQdzTOJxY+VDjYPog==","signatures":[{"sig":"MEQCIDmduhCkRgdPerUR6ABxHOUN/xNUJX5d6wENhciklTGUAiBhVJK26tLT/Ph9F1djTNO81mvkfVystbBUFnHwtaI/IQ==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":2783701},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"e185e139c5d3b18df03b34c023ec7416478688c8","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.29.0_1785591994987_0.445465742671032","host":"s3://npm-registry-packages-npm-production"}},"0.30.0":{"name":"clawmem","version":"0.30.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.30.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"f34d22a7acc94b2feb05e3e301eafbd0fb897292","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.30.0.tgz","fileCount":121,"integrity":"sha512-PBRgfwAbpDG9XCAYvVgjdY6bWlvUdJDLaGV7wj5G2zrWjdpTqIYhOPrrX+cAYaGXkfYV+LtBJ8I6tB89Xrpt/A==","signatures":[{"sig":"MEYCIQCbgwnO/hIkyyJ4d1+9+Xj0vXarWc8FMvC8GSLy+kewtwIhAIX4rLs82QUZCDfoyKyDJ4pDZDpSSujVRAVCkEMQAaXn","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":2794206},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"b166a50c9a93ef89240b9a4802bc771a6a608708","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.30.0_1785768689980_0.5555844099564187","host":"s3://npm-registry-packages-npm-production"}},"0.31.0":{"name":"clawmem","version":"0.31.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.31.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"b25557877b12934a32b320340ad97e99506df227","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.31.0.tgz","fileCount":121,"integrity":"sha512-DuBlD1VcHcYxceUzEYdYiBJ/hmfWbRDlLZAPNa2UaiGOO3ChncbTGFRLmst5ztZx9nxrLTHUppxtoJAZUULDTg==","signatures":[{"sig":"MEUCIQC8ucPCIT9xel6NNYKM+obWPY8A8rzUV7FwMl+kZBMPuQIgBd4Qq2OrpfX4DqlU4JxnRn3g+UNdfiSgsBWJpgDyr2k=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":2808657},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"622a011896d85e6a832915fc764f253173bb3ea4","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.31.0_1785841007031_0.6930318154935164","host":"s3://npm-registry-packages-npm-production"}},"0.32.0":{"name":"clawmem","version":"0.32.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.32.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"35242b7bc062b42b670c4c57766a1a0fd83cc29f","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.32.0.tgz","fileCount":122,"integrity":"sha512-H86zUjjIf/Lt86Y8IsuFs57SRyGc/LnWgTrSblDYv4bBqB3gjmIvLTUa1FJQVJOQRK4X13lx+Xnp5X/54NccEA==","signatures":[{"sig":"MEUCIQCzdTJEpB+aJ+15kqVAdKd6Dk3PYQuUW46qDANIcfJsDwIgHOteMlvg+7XDYV5Mq3GdbUXPWEedZIS0qXO8yAHpCNA=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":2840317},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"955c740a1117b9df046a1c4bfb12a05444e10dd3","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.32.0_1785858012113_0.6548409340767141","host":"s3://npm-registry-packages-npm-production"}},"0.33.0":{"name":"clawmem","version":"0.33.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.33.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"959e08f1698d02a9eb4705ec86a30159bf59d072","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.33.0.tgz","fileCount":124,"integrity":"sha512-LWO6t1T/T0tV1i+jbhNLIbHMHHx0zfIZKhAziNmGaYm8WqJwfOW3aEONPeEvQjE1q3HdPJOSm/UUciJTwXwHSw==","signatures":[{"sig":"MEQCICz/vNrYVhDXM1oGm6p0IWcM2ifV4SlhaGGKadyIWKDCAiBLUpt/zLjLanh+07dIYUB6eTVVpwJrzbl4mFWCKMbYdg==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":2937491},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"252d8b178d0308a2cdb98b980213287978695742","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.33.0_1785876929415_0.9020182110444395","host":"s3://npm-registry-packages-npm-production"}},"0.34.0":{"name":"clawmem","version":"0.34.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.34.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"8cc65fb17979f596b092e2c6f9aa5d31f7180d71","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.34.0.tgz","fileCount":124,"integrity":"sha512-z5h7fpx7LtxEnwTPRjB+qeIDEwiZhqA8Mz6CXU2DhJtebggltPmvbCQyjtwlkir0Leiq7H36GLaOJsgozHTpxw==","signatures":[{"sig":"MEQCIDHp+HRk66gVarNulmyqcKKsa+DbZa0MJUpgO+Krcc5fAiA0uKDecy88zR+YQMvW4JqnEbJtECwR0gUTzoio4fnuJA==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":2955132},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"4ac89f210ad2fdf36ebd7e835c146ed0bcb582dc","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.34.0_1785959366003_0.6534486538850697","host":"s3://npm-registry-packages-npm-production"}},"0.35.0":{"name":"clawmem","version":"0.35.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.35.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"ce3d8128b00a0b96669f3577207424b9c8708549","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.35.0.tgz","fileCount":124,"integrity":"sha512-BKIE/FgfSphJCkKZNW0jkvhjxw5Luq7TFj6VBeBFwuQMLGfsWh6f/0H8NCp8W+7efkPlw95s+EXZY8bSHsY+LA==","signatures":[{"sig":"MEYCIQDnE61BfJpGP5A6ECb1iHdjafKNnwR0sMnKi6fZBIHGlQIhAKL4LMjweaYEZ3oPUnckB4Ffw6Y8h5YETXRnvMdxjJnh","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":2959655},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"5194932bee7a7cfe4945c4d22861c17453dc8fa7","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.35.0_1786011345757_0.7943883296452874","host":"s3://npm-registry-packages-npm-production"}},"0.36.0":{"name":"clawmem","version":"0.36.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.36.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"16c36700144af3cdb0ac168d019b6e59753da5f1","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.36.0.tgz","fileCount":124,"integrity":"sha512-ssqEE+mUShNYt26s/31DI+SXTtw3OKZlf0bFvRyQiTJlI3LE7oSX/9Qrxf0yB6skTqTh9joibOHDAtUbFsMEcg==","signatures":[{"sig":"MEQCIB8b3f4jtuaYrJ+aTP/0bc3DM9RPAguwBk8zE7/VjZiZAiApqTaVpfCmGQwc1zAE3Nqrlurdjfblr3v0QLFvJO/0Lw==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":2989176},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"e986b9f67fc41b6b0ad6d5ab091bc6d6b766cac5","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.36.0_1786026391475_0.23115405796580246","host":"s3://npm-registry-packages-npm-production"}},"0.37.0":{"name":"clawmem","version":"0.37.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.37.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"6f6def0b04303ca6e9306bb1e81d0a7cf3fdd566","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.37.0.tgz","fileCount":124,"integrity":"sha512-tlfgQCTCjHHYjfk9gPOwJAHneRBlKOArjx+9pMDKnXnRuzyRPUExHIZfTdYX/3OcDOAb30BwFg0Fu6DkFHP3tg==","signatures":[{"sig":"MEQCICr82bxfaS1s1Q55Xqp+pCBXDLkOh1X9lI0JalTgJFqrAiAD2XIfPofA/F/XE9Qoe2q4A89Q+Y21s7f357/e1xeOFQ==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":3013501},"type":"module","engines":{"bun":">=1.0.0"},"scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.37.0_1787082131068_0.1899771553204157","host":"s3://npm-registry-packages-npm-production"}},"0.38.0":{"name":"clawmem","version":"0.38.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.38.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"1f60448e2185a9fac126144ad872ca10d4e41652","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.38.0.tgz","fileCount":138,"integrity":"sha512-7hLAyYVBNnvduWG3UfqGO3oDsJuDL/KxNEmhAfD7efiAfhITTiRJbkvsfSuYdeHFX0vzynJNeo1OTwF/oJU2BA==","signatures":[{"sig":"MEUCIAOFmU3xkT83jcJxESOVG8Av+m/olMhFPwgs6T7Kc+HTAiEAnj7H3aBbXYJMj2V982Tnsqq/u3uThdnbLvrTH0BwzRo=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"},{"sig":"MEUCIQCLXEymHk8EIh5hXPVipCkHMqv1RcI0+IHh6E9YGt+1DAIgV8dbIUweWlSOIskF3/5ZTwTdcArOwG61+z/jF3Sxa6Q=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":3745618},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"3798009515035e94820e23059f9d4caed122f6cd","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.38.0_1790413539063_0.08256302488942868","host":"s3://npm-registry-packages-npm-production"}},"0.38.1":{"name":"clawmem","version":"0.38.1","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.38.1","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"2a7f58da26c0e67135cfab317699e17d9d33e6e8","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.38.1.tgz","fileCount":138,"integrity":"sha512-4e7N0PSMRsTp3l2v+UHOhqDTbbBdZ/CnzpaMP1QOgS5evVhWcRy/LZocScwkCE87mGCBkW7aeXDV8LrUDoE6yA==","signatures":[{"sig":"MEQCIA+gtzfRBIq0gyDXvu7QxdLUaivf8anGFcWPIynrf+wYAiAGrSZP3MfO2npb/WJb1Wq+bUxy5Nyk564zNrAA9t/HPA==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"},{"sig":"MEYCIQCcXzxfl5FEj9mUyr+LeSI5Fq+hEZ4zltkWmDcroe1vrwIhANnnRv2CPP104fLcQxCZQH7FPeapJm9CnFcCK2LxgNyO","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":3747343},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"a24f8a822832d346b7e3f93fd45877f355b982f4","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.14.5","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.38.1_1790416947634_0.20067951873155598","host":"s3://npm-registry-packages-npm-production"}},"0.39.0":{"name":"clawmem","version":"0.39.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.39.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"64f57ab5e26df865e057b2e8de9ea2d028212df2","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.39.0.tgz","fileCount":138,"integrity":"sha512-fkvjUqlvsF4j+sj80crGAbEciK0I1XXrLoTnn6gIFsm08o5avMUyT7GAhUAm84ic7UgZzbYuSKpRHnRBB3RWbw==","signatures":[{"sig":"MEQCIH6xPVUm37RKjT52hRkfF18pRO9T5/drc7Ovc94bb4ETAiBEXBvUO8s9p4vDpJhE5VGnKAXJoXO3jP/cqeclp8wtug==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"},{"sig":"MEUCIETO2YTUBrMmBJKH4Xw9k5EasjdES1ssjpQuLURjyC2mAiEAgllCn+a5FDzEIA8ouEsA7esf8AP5hBa0pZmpIVD/Hd8=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":3818541},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"f912616848db9f50cdf00d5c1f182c98d2a0a0a5","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.20.0","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.39.0_1790443030588_0.0051014442972281415","host":"s3://npm-registry-packages-npm-production"}},"0.39.1":{"name":"clawmem","version":"0.39.1","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.39.1","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"d3327edcc48926c05fcb8217effae64a120b4b5f","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.39.1.tgz","fileCount":138,"integrity":"sha512-rqEEywWLMxwfcLjRhF1fG9ziI3AWg+BAJBj/9+YIxRmakRCa5lgok3Yi6Xl4pBV5Zoq2ahiXnxlURAwJ2Z16vg==","signatures":[{"sig":"MEQCIF5vTx/VKoFEnkzQLzUn1iswSn4ogv1p5OlHqUqp0e9PAiBW47hOXDowcQcAz9wkSessfu1wJc66bxSXgJKDOTUEtA==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"},{"sig":"MEUCIDtR3wVrom3eNKnWKtApxJzXJZHUvqc9dfyjJSOunOlAAiEAhZGKk0pn/NSnFj/5dHLceha2ymb2QSLQ4gK4FbsQIFQ=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":3854057},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"39419a13d062ed98711da93d3119f5e486f81636","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.20.0","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.39.1_1790564224055_0.293013728874403","host":"s3://npm-registry-packages-npm-production"}},"0.40.0":{"name":"clawmem","version":"0.40.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.40.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"c767382e96dc438dbb77ed9d4189b46d558a83b8","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.40.0.tgz","fileCount":140,"integrity":"sha512-UrD9XHIo8kub093D+Cm2YZS+w3xsHdqrebz9nwHAJBTvNVworc6wJ2X4sULbeJhGMMMmrdhNYCM/TQV+BJU54g==","signatures":[{"sig":"MEUCICNYi5WttuB8WB3Y/m58uN9G4DwC5gn9zzx8PEEF3Rn7AiEAt46Kv+3i953M9jKhmhnLQpr/aQHX3xL6mimY1BVCXsk=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"},{"sig":"MEQCIEG5l2/B5gEBh+sCS1xuKyXTnwyVpe1C5C3a7NS9+U8ZAiBnos1XFtSdu/QpMDlhxyzknRddFr5WqazDnW+CH10n6w==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":3936383},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"5ccce97a8f3d46387f00e8110fe0f58f1596d547","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.20.0","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.40.0_1790612437098_0.08012263877664605","host":"s3://npm-registry-packages-npm-production"}},"0.40.1":{"name":"clawmem","version":"0.40.1","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.40.1","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"90ff5b46ffbbe313320d38bcded7cad64190fdba","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.40.1.tgz","fileCount":140,"integrity":"sha512-4djha67JqYEHczQPm9vMwt6f+EcDNOZD5xmkXt6RU794dzgMC/ZfWWFbQ5VUH62MfvN5EmgpTF02zBwNKXCfOA==","signatures":[{"sig":"MEUCIEtZxucNajDd40pE9A26VQqPYDMzB99CHnfBmr//Ni30AiEAoLq8pfCNuDWJjrY7zwGvl+1bo4qbi4G4FoLP81I2k1k=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"},{"sig":"MEUCIQDcpOlZ+XGaINjzx3hwrY3eNGFQfNp9n7AlwscomBVxeQIgPwSw1EjUcrJ97Kmes234Sin0dl1KNPfIVRdTH6dzl+0=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":3945228},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"6e591361e655909e194a9820c5c92b18eaa1b940","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.20.0","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.40.1_1790651159326_0.1820032997825214","host":"s3://npm-registry-packages-npm-production"}},"0.40.2":{"name":"clawmem","version":"0.40.2","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.40.2","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"71d48062c17451f52402e167fe8ad98cdbffe1d1","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.40.2.tgz","fileCount":140,"integrity":"sha512-HFcsKPOGnM6cBK+z1uU75TvjLbS8CAsom3k5aJzfjDl2OHEBVmuAqgbBco4i3V9qrvo/yllXyRmDVeQCCrGYrw==","signatures":[{"sig":"MEUCIQD8HqqdU1M9Zwu1QJTMkGte8CyN0BMbDWS58hlUjfa2tQIgKxuoCrpvK4xreSTjkMdAb0L5qPSGqgksTtmOqdG5FUE=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"},{"sig":"MEUCIBbCPFPdWvl2k5upvIwrlr8VyrQx3nsoQ2CPcEND0hX+AiEAjADD/MUH7s1BZeXAdicW+vvmEMOchlGyh8RLXhqKYvc=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":3958142},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"cef3093868c586ba2ddd057d6202c90c940abba1","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.20.0","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.40.2_1790658278844_0.8393453611456634","host":"s3://npm-registry-packages-npm-production"}},"0.40.3":{"name":"clawmem","version":"0.40.3","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.40.3","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"655050f49ad52942cbc643607e6c7a20d06ccb4d","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.40.3.tgz","fileCount":140,"integrity":"sha512-QoNqBXJt+NNRZPQtPGhvJJ+rkX2wmyOGn7R71SLh3ZUW2CvqvsCmrWYPAoc80b2HPM2dcRSfjzasdS1SvqGwRA==","signatures":[{"sig":"MEYCIQCmyE8cQQ5Nak+1nI2ydbNPLlDFwYuLX90hm1yH5FGpPwIhAPc6SZmLyvdOoYGB1C1BjdSGwV6/Fnl0BHXgkkusmn4e","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"},{"sig":"MEYCIQCj0w+ESJlywftNpMiFxbEurb2psT8HvpdSrYgr31sQXQIhANdV9+NveMX0A/5kWLj+jThUkRDT11nQhuiUzyJuEmNA","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":3978650},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"8e2579a75e3510d6765ecdbf796bebf40d9d8d5e","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.20.0","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.40.3_1790669928343_0.49894020768249736","host":"s3://npm-registry-packages-npm-production"}},"0.41.0":{"name":"clawmem","version":"0.41.0","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.41.0","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"25c5e216ee703f37855b43e31bc063d854310ba9","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.41.0.tgz","fileCount":157,"integrity":"sha512-/33mq+vvP3qb3z6kBJeb3FVmHG1PEu7erAGsqkN0HNn9TClEuCWc1GHqg3Ji0g5l7jaAxPmUyvdyNj7dFrOMkw==","signatures":[{"sig":"MEUCIQDeswTuQW5iLDV253w+6GdMxLMcZ6g5X/moc3tWBmTrUAIgWAWMd+OTcfPtAJle1fjXsSgXEwMjCB0rmjSrYjXnoWk=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"},{"sig":"MEUCIDfnQuqQ5rbGYoIZXnLpwNa67v+2bJjqps7Bx7H8b+7VAiEA0++iSbmn1D1v9ey4mQCrE4+9XSPycX1v7WQTbTyeFL0=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":4316070},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"24a2df53aeec69d84f1799f99d815bc492ea167e","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.20.0","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.41.0_1790799538233_0.7368248151563404","host":"s3://npm-registry-packages-npm-production"}},"0.41.1":{"name":"clawmem","version":"0.41.1","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.41.1","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"a80fe9f0910445866f2dc138deea836ae6a0cdf6","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.41.1.tgz","fileCount":157,"integrity":"sha512-rLbAHR0paRhRsCxzJ/1P55NMUdYY1/2ePXy21kuFZU/08394CbH3JOAXsnrED/D92el+Tb/qZKnpYstVaRH6UA==","signatures":[{"sig":"MEYCIQDlXWywds27zngggdp8BIKEamrMIMJdmlNYoaGm1H0p1AIhAOtibtmkwZa/JJBnHLobfYAD4kZAGsYYgReI2krSlUuB","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"},{"sig":"MEUCIFptREUxQKdQcmXnM4EEX5eAHFIZFHKk3j5kNGWaPrXWAiEAjMCabUVbjHc/hNT5qLb7wBuZLBOG1ZDYd3iS5THuUOY=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":4326384},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"2b77a06a29eee3db58e4f31dd9ee14e33bf23d82","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.20.0","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.41.1_1790823119901_0.30654687028332184","host":"s3://npm-registry-packages-npm-production"}},"0.41.2":{"name":"clawmem","version":"0.41.2","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"author":{"name":"yoloshii"},"license":"MIT","_id":"clawmem@0.41.2","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"homepage":"https://github.com/yoloshii/ClawMem#readme","bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"bin":{"clawmem":"bin/clawmem"},"dist":{"shasum":"eb76fb33db7c703c8f69b7af6f689b804ec76eaa","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.41.2.tgz","fileCount":158,"integrity":"sha512-2d910VxdXQ3rXWbWQBCESvXnIdnZCiVJSI3lBjGGx6n78a3Ew2+CL/R3NhJpv/vNwSU3xA2ZHqTzUy0EDu2rLw==","signatures":[{"sig":"MEUCIQDYmZenmPNfb2Cinfjc6Wc55oE/2xxW2oWUEBD+g4R7ngIgE8xnPzNR8ejcoH4FFHUcNodur5XkYBonFENO4OZ1R/k=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"},{"sig":"MEYCIQCLQB/EnRUuhdEBBXtu4qFluByCuiTvfeOYx9FxA5G76AIhANUaO+r2N7S/S03kXyTtQNQXz6csnASxjMOIy1erUYp6","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":4447660},"type":"module","engines":{"bun":">=1.0.0"},"gitHead":"4571a7b2b1140192dec77fb71190f0c61ca2a334","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.20.0","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"tmp":"tmp/clawmem_0.41.2_1790870574658_0.07767230097341837","host":"s3://npm-registry-packages-npm-production"}},"0.41.3":{"_id":"clawmem@0.41.3","bin":{"clawmem":"bin/clawmem"},"bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"dist":{"shasum":"e95a831a40e5ffc85c7f67b5082e04c975cc9f01","tarball":"https://registry.npmjs.org/clawmem/-/clawmem-0.41.3.tgz","fileCount":158,"integrity":"sha512-Y3aD1mKnzz8DJh8cXXi8qvJDUE06/LMROQhOY4RBJTvZCFGZJWw0IDj6me7mSs05aa6WuixaTBOqN6TKvxi3vw==","signatures":[{"sig":"MEUCIQDq3WFlYgeD2kfEvXiH7sdPLIgtQl0LvJYkTWoTZih7/AIgDSbiLeYy6obBLA1t/FnG8fMErISWUbtrXlCRI8IquDs=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"},{"keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U","sig":"MEUCICr4CmzSWqK6s0+cfogvDjVOOumE6jefekpHnL189/PhAiEA3JhDn+oL63Y9xBirKC21X+4/8qeOAC55PTM1lNZhncg="}],"unpackedSize":4463435},"name":"clawmem","type":"module","author":{"name":"yoloshii"},"engines":{"bun":">=1.0.0"},"gitHead":"74a27097eb0c04765cf2f7530bde5ef9255ecf81","license":"MIT","scripts":{"dev":"bun src/clawmem.ts","test":"bun test","inspector":"npx @modelcontextprotocol/inspector bun src/clawmem.ts mcp"},"version":"0.41.3","_npmUser":{"name":"yoloshii","email":"drekonrad@gmail.com"},"homepage":"https://github.com/yoloshii/ClawMem#readme","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"_npmVersion":"11.12.1","description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","directories":{},"maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"_nodeVersion":"20.19.2","dependencies":{"zod":"^4.2.1","yaml":"^2.8.2","sqlite-vec":"^0.1.7-alpha.2","gray-matter":"^4.0.3","node-llama-cpp":"^3.20.0","@modelcontextprotocol/sdk":"^1.25.1"},"_hasShrinkwrap":false,"devDependencies":{"@types/bun":"latest"},"peerDependencies":{"typescript":"^5.9.3"},"optionalDependencies":{"sqlite-vec-linux-x64":"^0.1.7-alpha.2","sqlite-vec-win32-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-x64":"^0.1.7-alpha.2","sqlite-vec-darwin-arm64":"^0.1.7-alpha.2"},"_npmOperationalInternal":{"host":"s3://npm-registry-packages-npm-production","tmp":"tmp/clawmem_0.41.3_1790961583965_0.770421767350572"}}},"time":{"created":"2026-03-15T11:39:45.209Z","modified":"2026-10-02T17:19:44.250Z","0.1.0":"2026-03-15T11:39:45.427Z","0.1.1":"2026-03-16T01:30:34.520Z","0.1.2":"2026-03-16T06:48:02.038Z","0.1.3":"2026-03-16T22:47:00.413Z","0.1.4":"2026-03-16T23:45:46.600Z","0.1.5":"2026-03-17T00:13:25.229Z","0.1.6":"2026-03-17T06:29:54.193Z","0.1.7":"2026-03-17T08:10:27.391Z","0.1.8":"2026-03-20T13:09:26.653Z","0.2.0":"2026-03-23T18:44:38.872Z","0.2.1":"2026-03-23T19:35:55.477Z","0.2.2":"2026-03-23T20:19:50.487Z","0.2.3":"2026-03-24T05:22:18.127Z","0.2.4":"2026-03-24T14:37:24.275Z","0.2.5":"2026-03-25T10:49:30.778Z","0.2.6":"2026-03-25T12:40:01.802Z","0.2.7":"2026-03-28T15:52:06.796Z","0.2.8":"2026-03-30T14:32:40.828Z","0.2.9":"2026-03-31T08:45:47.571Z","0.3.0":"2026-03-31T09:42:50.044Z","0.3.2":"2026-04-02T13:21:34.771Z","0.3.3":"2026-04-02T14:00:36.492Z","0.3.4":"2026-04-02T14:31:40.033Z","0.4.1":"2026-04-04T18:51:57.712Z","0.4.2":"2026-04-04T19:14:45.074Z","0.5.0":"2026-04-08T04:09:45.291Z","0.5.1":"2026-04-08T06:02:57.285Z","0.6.0":"2026-04-08T07:59:01.274Z","0.7.0":"2026-04-08T10:59:44.214Z","0.7.1":"2026-04-09T19:59:03.802Z","0.7.2":"2026-04-09T21:14:59.387Z","0.8.0":"2026-04-09T22:11:47.981Z","0.8.1":"2026-04-09T22:52:32.052Z","0.8.2":"2026-04-10T01:15:47.528Z","0.8.3":"2026-04-10T04:02:23.011Z","0.8.4":"2026-04-11T14:28:04.177Z","0.8.5":"2026-04-13T00:12:49.696Z","0.9.0":"2026-04-13T04:09:11.657Z","0.10.0":"2026-04-13T13:48:02.012Z","0.10.1":"2026-04-19T04:06:16.507Z","0.10.2":"2026-04-28T12:41:50.562Z","0.10.3":"2026-05-04T10:49:03.003Z","0.10.4":"2026-05-08T10:25:08.271Z","0.10.5":"2026-05-15T10:03:41.963Z","0.10.6":"2026-05-20T15:11:45.578Z","0.10.7":"2026-05-20T19:28:45.753Z","0.11.0":"2026-06-22T20:40:52.975Z","0.11.2":"2026-06-23T20:02:39.631Z","0.11.3":"2026-06-24T17:27:06.527Z","0.12.0":"2026-06-25T09:23:46.979Z","0.13.0":"2026-06-25T14:39:24.029Z","0.14.0":"2026-06-25T19:59:45.610Z","0.15.0":"2026-06-30T13:08:29.410Z","0.15.1":"2026-06-30T15:16:39.564Z","0.16.0":"2026-07-01T16:03:41.962Z","0.17.0":"2026-07-01T20:22:23.309Z","0.18.0":"2026-07-04T16:18:54.342Z","0.19.0":"2026-07-04T19:39:46.749Z","0.20.0":"2026-07-05T14:45:12.066Z","0.20.2":"2026-07-07T08:53:35.317Z","0.21.0":"2026-07-10T07:11:34.515Z","0.22.0":"2026-07-10T10:07:13.095Z","0.23.0":"2026-07-10T11:31:15.372Z","0.24.0":"2026-07-10T15:50:01.192Z","0.25.0":"2026-07-18T04:39:25.288Z","0.26.0":"2026-07-18T06:06:24.124Z","0.27.0":"2026-07-18T08:31:03.739Z","0.28.0":"2026-07-19T16:20:44.724Z","0.29.0":"2026-08-01T13:46:35.230Z","0.30.0":"2026-08-03T14:51:30.195Z","0.31.0":"2026-08-04T10:56:47.259Z","0.32.0":"2026-08-04T15:40:12.271Z","0.33.0":"2026-08-04T20:55:29.592Z","0.34.0":"2026-08-05T19:49:26.261Z","0.35.0":"2026-08-06T10:15:45.938Z","0.36.0":"2026-08-06T14:26:31.692Z","0.37.0":"2026-08-18T19:42:11.265Z","0.38.0":"2026-09-26T09:05:39.201Z","0.38.1":"2026-09-26T10:02:27.787Z","0.39.0":"2026-09-26T17:17:10.744Z","0.39.1":"2026-09-28T02:57:04.215Z","0.40.0":"2026-09-28T16:20:37.240Z","0.40.1":"2026-09-29T03:05:59.461Z","0.40.2":"2026-09-29T05:04:38.963Z","0.40.3":"2026-09-29T08:18:48.460Z","0.41.0":"2026-09-30T20:18:58.388Z","0.41.1":"2026-10-01T02:52:00.052Z","0.41.2":"2026-10-01T16:02:54.814Z","0.41.3":"2026-10-02T17:19:44.110Z"},"bugs":{"url":"https://github.com/yoloshii/ClawMem/issues"},"author":{"name":"yoloshii"},"license":"MIT","homepage":"https://github.com/yoloshii/ClawMem#readme","keywords":["mcp-server","model-context-protocol","claude-code","ai-agent-memory","retrieval-augmented-generation","rag","vector-search","sqlite","bun","llama-cpp","local-first","context-engine","openclaw","mcp-tools","hybrid-search"],"repository":{"url":"git+https://github.com/yoloshii/ClawMem.git","type":"git"},"description":"On-device memory layer for AI agents. Claude Code, OpenClaw, and Hermes. Hooks + MCP server + hybrid RAG search.","maintainers":[{"name":"yoloshii","email":"drekonrad@gmail.com"}],"readme":"# ClawMem — On-device memory layer for Claude Code, OpenClaw, and Hermes agents\n\n<p align=\"center\">\n  <img src=\"docs/clawmem_hero.jpg\" alt=\"ClawMem\" width=\"100%\">\n</p>\n\n**On-device memory for Claude Code, OpenClaw, Hermes, and AI agents.** Retrieval-augmented search, hooks, and an MCP server in a single local system. No API keys, no cloud dependencies.\n\nClawMem fuses recent research into a retrieval-augmented memory layer that agents actually use. The hybrid architecture combines [QMD](https://github.com/tobi/qmd)-derived multi-signal retrieval (BM25 + vector search + reciprocal rank fusion + query expansion + cross-encoder reranking), [SAME](https://github.com/sgx-labs/statelessagent)-inspired composite scoring (recency decay, confidence, content-type half-lives, co-activation reinforcement), [MAGMA](https://arxiv.org/abs/2501.13956)-style intent classification with multi-graph traversal (semantic, temporal, and causal beam search), and [A-MEM](https://arxiv.org/abs/2510.02178) self-evolving memory notes that enrich documents with keywords, tags, and causal links between entries. Pattern extraction from [Engram](https://github.com/Gentleman-Programming/engram) adds deduplication windows, frequency-based durability scoring, and temporal navigation.\n\nIntegrates via Claude Code hooks, an MCP server (works with any MCP-compatible client), a native OpenClaw plugin, or a Hermes Agent `MemoryProvider` plugin. All paths write to the same local SQLite vault. A decision captured during a Claude Code session shows up immediately when an OpenClaw or Hermes agent picks up the same project.\n\nTypeScript on Bun. MIT License.\n\n## What It Does\n\nClawMem turns your markdown notes, project docs, and research dumps into persistent memory for AI coding agents. It automatically:\n\n- **Surfaces relevant context** on every prompt (context-surfacing hook)\n- **Bootstraps sessions** with your profile, latest handoff, recent decisions, and stale notes\n- **Captures decisions, preferences, milestones, and problems** from session transcripts using a local GGUF observer model\n- **Imports conversation exports** from Claude Code, ChatGPT, Claude.ai, Slack, and plain text via `clawmem mine`, with optional post-import LLM fact extraction (`--synthesize`) that pulls structured decisions / preferences / milestones / problems and cross-fact links out of otherwise full-text conversation dumps (v0.7.2). Imports preserve **authorship time** (v0.27.0): ranking recency and temporal queries run on when content was actually written, so historical conversations mined today don't rank as fresh — with a metadata-only `--backfill-dates` lane for vaults mined earlier\n- **Generates handoffs** at session end so the next session can pick up where you left off\n- **Learns what matters** via a feedback loop that boosts referenced notes and decays unused ones\n- **Guards against prompt injection** in surfaced content\n- **Classifies query intent** (WHY / WHEN / ENTITY / WHAT) to weight search strategies\n- **Traverses multi-graphs** (semantic, temporal, causal) via adaptive beam search\n- **Evolves memory metadata** as new documents create or refine connections\n- **Infers causal relationships** between facts extracted from session observations\n- **Detects contradictions** between new and prior decisions, auto-decaying superseded ones — when a contradiction **judge** is configured (`CLAWMEM_JUDGE_*`, v0.29.0; disabled otherwise) (with an additional merge-time contradiction gate in the consolidation worker that blocks cross-observation contradictions before they land, v0.7.1)\n- **Guards against cross-entity merges** during consolidation — name-aware dual-threshold merge safety compares entity anchors before merging similar observations, preventing \"Alice decided X\" from merging into \"Bob decided X\" (v0.7.1)\n- **Prevents context bleed in derived insights** — the Phase 3 deductive synthesis pipeline validates every draft against an anti-contamination wrapper (deterministic entity contamination check + LLM validator + dedupe) before writing cross-session deductive observations (v0.7.1)\n- **Frames surfaced facts as background knowledge** — `context-surfacing` wraps injected content in `<instruction>` + `<facts>` + `<relationships>` blocks, telling the model to treat facts as already-known and exposing memory-graph edges between surfaced docs directly in-prompt (v0.7.1)\n- **Injects knowledge-graph facts as structured triples** — when the user's prompt mentions entities already known to the vault, `context-surfacing` resolves them via a three-path prompt-only extractor (canonical IDs, proper nouns, lowercased n-grams), queries the SPO graph for current-state triples, and appends a `<vault-facts>` block of raw `subject predicate object` lines to `<vault-context>` — off for `speed`, 200 tokens on `balanced`, 250 on `deep`, token-truncated at the triple boundary (v0.9.0)\n- **Session-scoped focus topic** — `clawmem focus set \"<topic>\" --session-id <id>` writes a per-session focus file used as a snippet-selection intent: surfaced docs prefer sentences matching the topic. Presentation only since v0.38.0 — a focus never changes expansion, reranking, scoring, ordering, or the surfaced set — session-isolated, fail-open, never writes to SQLite or lifecycle columns (v0.9.0, narrowed v0.38.0)\n- **Ranks hook injections on one channel-aware key** — every retrieval leg (BM25, vector, file-aware, gated prior-turn, expansion variants) contributes a ranked lane; weighted reciprocal-rank fusion yields a single ordering key (current-support band, fused mass) that decides membership, final order, AND admission — no mixed raw-score sorts, no metadata reordering (v0.38.0)\n- **Admits by relevance, abstains honestly** — the context-surfacing hook admits candidates by a relative floor on the fused ordering key and abstains at query level when current-turn support is missing or keyword-degenerate, instead of surfacing weak lists (v0.38.0)\n- **Guards the deep rerank lane** — cross-encoder scores apply only under full candidate coverage AND a discriminating score set (degeneracy gate); the reranker joins the final order as a rank-fused lane, and remote rerank scores are cached only under an attested provider identity (`clawmem rerank-health`) (v0.38.0)\n- **Keeps the hook's write path off your prompt latency** — turn alignment is one early fail-closed row; recall attribution, token accounting, and vault mirrors are handed to a detached drainer process through an on-disk spool after the payload is emitted (v0.38.0)\n- **Scores document quality** using structure, keywords, and metadata richness signals\n- **Boosts co-accessed documents** — notes the agent verifiably referenced together in one turn (v0.41.0) get retrieval reinforcement on the composite MCP surfaces (removed from hook ordering in v0.38.0 — the injected order is the channel-aware fusion key alone)\n- **Decomposes complex queries** into typed retrieval clauses (BM25/vector/graph) for multi-topic questions\n- **Cleans stale embeddings** automatically before embed runs, removing orphans from deleted/changed documents\n- **Transaction-safe indexing** — crash mid-index leaves zero partial state (atomic commit with rollback)\n- **Processes each turn once** — the extraction and handoff hooks keep a cursor per transcript and the feedback hook decides each surfaced turn once (v0.41.0), so a turn is extracted, summarised and credited once instead of again at every response, and each session's documents are its own\n- **Navigates temporal neighborhoods** around any document via the `timeline` tool — progressive disclosure from search to chronological context to full content\n- **Boosts frequently-revised memories** — documents with higher revision counts get a durability signal in composite scoring (capped at 10%)\n- **Supports pin/snooze lifecycle** for persistent boosts and temporary suppression\n- **Manages document lifecycle** — policy-driven archival sweeps with restore capability\n- **Auto-routes queries** via `memory_retrieve` — classifies intent and dispatches to the optimal search backend\n- **Syncs project issues** from Beads issue trackers into searchable memory\n- **Runs a quiet-window heavy maintenance lane** — a second consolidation worker, off by default behind `CLAWMEM_HEAVY_LANE=true`, that runs on a longer interval only inside a configurable hour window. Gated by `context_usage` query-rate so it never competes for CPU/GPU with interactive sessions, scoped exclusively via DB-backed `worker_leases`, stale-first by default with an optional surprisal selector, and journals every attempt in `maintenance_runs` for operator visibility (v0.8.0)\n\nRuns fully local with no API keys and no cloud services. Integrates via Claude Code hooks and MCP tools, as a native OpenClaw plugin, or as a Hermes Agent `MemoryProvider` plugin. All modes share the same vault for cross-runtime memory. Works with any MCP-compatible client.\n\nFull version history is in [RELEASE_NOTES.md](RELEASE_NOTES.md). Upgrade instructions for existing vaults are in [docs/guides/upgrading.md](docs/guides/upgrading.md).\n\n## Architecture\n\n<p align=\"center\">\n  <img src=\"docs/clawmem-architecture.png\" alt=\"ClawMem Architecture\" width=\"100%\">\n</p>\n\n## Install\n\n### Platform Support\n\n| Platform | Status | Notes |\n|---|---|---|\n| **Linux** | Full support | Primary target. systemd services for watcher + embed timer. |\n| **macOS** | Full support | Homebrew SQLite handled automatically. GPU via Metal (llama.cpp). |\n| **Windows (WSL2)** | Full support | Recommended for Windows users. Install Bun + ClawMem inside WSL2. |\n| **Windows (native)** | Not recommended | Bun and sqlite-vec work, but `bin/clawmem` wrapper is bash, hooks expect bash commands, and systemd services have no equivalent. Use WSL2 instead. |\n\n### Prerequisites\n\n**Required:**\n\n- [Bun](https://bun.sh) v1.0+ — runtime for ClawMem. On Linux, install via `curl -fsSL https://bun.sh/install | bash` (not snap — snap Bun cannot read stdin, which breaks hooks).\n- SQLite with FTS5 — included with Bun. On macOS, install `brew install sqlite` for extension loading support (ClawMem detects and uses Homebrew SQLite automatically).\n\n**Optional (for better performance):**\n\n- [llama.cpp](https://github.com/ggml-org/llama.cpp) (`llama-server`) — for dedicated GPU inference. Without it, `node-llama-cpp` runs models in-process (auto-downloads on first use). GPU servers give better throughput and prevent silent CPU fallback.\n- systemd (Linux) or launchd (macOS) — for persistent background services (watcher, embed timer, GPU servers). ClawMem ships systemd unit templates; macOS users can create equivalent launchd plists. See [systemd services](docs/guides/systemd-services.md).\n\n**Optional integrations:**\n\n- [Claude Code](https://docs.anthropic.com/en/docs/claude-code) — for hooks + MCP integration\n- [OpenClaw](https://github.com/openclaw/openclaw) — for native plugin integration\n- [Hermes Agent](https://github.com/NousResearch/hermes-agent) — for `MemoryProvider` plugin integration\n- [bd CLI](https://github.com/gastownhall/beads) v0.58.0+ (verified through v1.1.0) — for Beads issue tracker sync (only if using Beads)\n\n### Install from npm (recommended)\n\n```bash\nnpm install -g clawmem\n```\n\nIf you use Bun as your package manager:\n\n```bash\nbun add -g clawmem\n```\n\n### Install from source\n\n```bash\ngit clone https://github.com/yoloshii/clawmem.git ~/clawmem\ncd ~/clawmem && bun install\nln -sf ~/clawmem/bin/clawmem ~/.bun/bin/clawmem\n```\n\n### Setup roadmap\n\nAfter installing, here's the full journey from zero to working memory:\n\n| Step | What | How | Details |\n|------|------|-----|---------|\n| **1. Bootstrap** | Create a vault, index your first collection, embed, install hooks and MCP | `clawmem bootstrap ~/notes --name notes` | One command does it all. Or run each step manually (see below). |\n| **2. Choose models** | Pick embedding + reranker models based on your hardware | 16GB+ VRAM → SOTA stack (zembed-1 + zerank-2). Less → QMD native combo. No GPU → cloud embedding or CPU fallback. | [Inference services](docs/guides/inference-services.md) |\n| **3. Download models** | Get the model files for your chosen stack (GGUFs for all three services; for zerank-2, only a GGUF that carries its score head works) | `wget` from HuggingFace, let `node-llama-cpp` auto-download the QMD native models, or build the zerank-2 bf16 sidecar | [Inference services](docs/guides/inference-services.md) |\n| **4. Start services** | Run GPU servers (if using dedicated GPU) and background services. Optionally enable the v0.8.2 background maintenance workers in the watcher unit so consolidation + deductive synthesis run automatically. | `llama-server` for each model. systemd units for watcher + embed timer. Drop-in for the watcher to enable workers + tune intervals + set the quiet window. | [systemd services](docs/guides/systemd-services.md), [background workers](docs/guides/systemd-services.md#background-maintenance-workers-v082) |\n| **5. Decide what to index** | Add collections for your projects, notes, research, and domain docs | `clawmem collection add ~/project --name project` | The more relevant markdown you index, the better retrieval works. See [building a rich context field](docs/introduction.md#building-a-rich-context-field). |\n| **6. Connect your agent** | Hook into Claude Code, OpenClaw, Hermes, or any MCP client | `clawmem setup hooks && clawmem setup mcp` for Claude Code. `clawmem setup openclaw` for OpenClaw. Copy `src/hermes/` to Hermes plugins for Hermes. | [Integration](#integration) |\n| **7. Verify** | Confirm everything is working | `clawmem doctor` (full health check) or `clawmem status` (quick index stats) | [Verify Installation](#verify-installation) |\n\n**Fastest path:** Step 1 alone gets you a working system with in-process CPU/GPU inference and default models — no manual model downloads or service configuration needed. Steps 2-4 are optional upgrades for better performance. Steps 5-6 are where you customize what gets indexed and how your agent connects.\n\n**Customize what gets indexed:** Each collection has a `pattern` field in `~/.config/clawmem/config.yaml` (default: `**/*.md`). Tailor it per collection — index project docs, research notes, decision records, Obsidian vaults, or anything else your agents should know about. The more relevant content in the vault, the better retrieval works. See the [quickstart](docs/quickstart.md#customize-index-patterns) for config examples.\n\n### Quick start commands\n\n```bash\n# One command: init + index + embed + hooks + MCP\nclawmem bootstrap ~/notes --name notes\n\n# Or step by step:\nclawmem init\nclawmem collection add ~/notes --name notes\nclawmem update --embed\nclawmem setup hooks\nclawmem setup mcp\n\n# Add more collections (the more you index, the richer retrieval gets)\nclawmem collection add ~/projects/myapp --name myapp\nclawmem collection add ~/research --name research\nclawmem update --embed\n\n# Verify\nclawmem doctor\n```\n\n### Upgrading\n\n```bash\nbun update -g clawmem   # or: npm update -g clawmem\n```\n\nDatabase schema migrates automatically on next startup (new tables and columns are added via `CREATE IF NOT EXISTS` / `ALTER TABLE ADD COLUMN`).\n\nAfter **major version updates** (e.g. 0.1.x → 0.2.0) that add new enrichment pipelines, run a full enrichment pass to backfill existing documents:\n\n```bash\nclawmem reindex --enrich  # Full enrichment: entity extraction + links + evolution for all docs\nclawmem embed             # Re-embed if upgrading embedding models (not needed for most updates)\n```\n\n`--enrich` forces the complete A-MEM pipeline (entity extraction, link generation, memory evolution) on all documents, not just new ones. Without it, reindex only refreshes metadata for existing docs.\n\nRoutine patch updates (e.g. 0.2.0 → 0.2.1) do not require reindexing.\n\nFor version-specific upgrade notes (opt-in features, optional cleanup steps, verification commands), see [docs/guides/upgrading.md](docs/guides/upgrading.md).\n\n### Integration\n\n#### Claude Code\n\nClawMem integrates via hooks (`settings.json`) and an MCP stdio server. Hooks handle 90% of retrieval automatically - the agent never needs to call tools for routine context.\n\n```bash\nclawmem setup hooks    # Install lifecycle hooks (SessionStart, UserPromptSubmit, Stop, PreCompact)\nclawmem setup mcp      # Register MCP server in ~/.claude.json (33 tools)\n```\n\n**Automatic (90%):** `context-surfacing` injects relevant memory on every prompt. `postcompact-inject` re-injects state after compaction. `decision-extractor`, `handoff-generator`, `feedback-loop` capture session state on stop.\n\n**Agent-initiated (10%):** MCP tools (`query`, `intent_search`, `find_causal_links`, `timeline`, etc.) for targeted retrieval when hooks don't surface what's needed.\n\n#### OpenClaw\n\nClawMem registers as a native OpenClaw memory plugin (`kind: memory`, v0.10.0+). Same 90/10 automatic retrieval, delivered through OpenClaw's plugin-hook bus instead of Claude Code hooks.\n\n```bash\n# v0.10.4+: profile-aware. Delegates to `openclaw plugins install --force` when the OpenClaw CLI\n# is on PATH (auto-enables the plugin, honors OPENCLAW_STATE_DIR, OPENCLAW_CONFIG_PATH, --profile).\n# Falls back to a recursive copy honoring OPENCLAW_STATE_DIR when the CLI is absent.\nclawmem setup openclaw\n\n# Custom profile (e.g. dev profile at ~/.openclaw-dev):\nOPENCLAW_STATE_DIR=~/.openclaw-dev clawmem setup openclaw\n```\n\n**What the plugin provides:**\n- **`before_prompt_build` hook (load-bearing)** - prompt-aware retrieval (context-surfacing + session-bootstrap) AND the pre-emptive `precompact-extract` run when token usage approaches the compaction threshold. This is the authoritative path for precompact state capture because it runs synchronously before the LLM call that would trigger compaction, so it cannot race the compactor.\n- **`agent_end` hook** - decision extraction, handoff generation, feedback loop (parallel, fire-and-forget at the OpenClaw call site). OpenClaw v2026.4.26+ also enforces a 30s default void-hook timeout on `agent_end` — slow handlers are logged but the underlying postrun work is not cancelled (fail-open).\n- **`before_compaction` hook (defense-in-depth fallback)** - fires `precompact-extract` again for the rare case where `before_prompt_build`'s proximity heuristic missed a sudden token-count jump. Fire-and-forget at OpenClaw's call site, so it races the compactor and offers no correctness guarantee on its own — the `before_prompt_build` path is what actually holds the invariant.\n- **`session_start` hook** - session registration + cached first-turn bootstrap context\n- **5 agent tools** - `clawmem_search`, `clawmem_get`, `clawmem_session_log`, `clawmem_timeline`, `clawmem_similar`\n\nDisable OpenClaw's native memory search to avoid duplicate injection:\n```bash\nopenclaw config set agents.defaults.memorySearch.extraPaths \"[]\"\n```\n\nClawMem coexists cleanly with OpenClaw's [Active Memory](https://docs.openclaw.ai/concepts/active-memory) plugin (v2026.4.10+) and, on OpenClaw v2026.4.18+ (#65411), with the `memory-core` dreaming sidecar — both run alongside ClawMem instead of being mutually exclusive. They search different backends and inject into different prompt regions, so they do not conflict. See the [OpenClaw plugin guide — Active Memory coexistence](docs/guides/openclaw-plugin.md#coexistence-with-openclaw-active-memory) and the [memory-core dreaming sidecar section](docs/guides/openclaw-plugin.md#coexistence-with-memory-core-dreaming-sidecar) for the two patterns.\n\n**Pair ClawMem (memory) with a context-engine plugin (v0.10.0+).** OpenClaw and Hermes maintainers have converged on a two-surface plugin model: one slot for memory plugins (cross-session, retrieval-first) and a separate slot for context-engine plugins (in-session, compression/compaction-first). Under that model ClawMem is a memory layer — it has always been one in Hermes via the `MemoryProvider` ABC, and v0.10.0 moves the OpenClaw integration to the same semantic slot. You can now run ClawMem in the `memory` slot alongside an LCM-style compression plugin (for example, `lossless-claw`) in the `context-engine` slot. The two plugins do not overlap: one persists across sessions, the other reshapes the live window. See the [OpenClaw plugin guide — memory vs context engine](docs/guides/openclaw-plugin.md#memory-vs-context-engine--the-dual-plugin-surface) for the full rationale.\n\n> **OpenClaw v2026.4.11+ recommended (required for ClawMem v0.10.0+).** v2026.4.11 introduced a new plugin discovery contract that requires each plugin directory to ship a `package.json` with `openclaw.extensions` declared, and that rejects symlinked plugin directories. ClawMem v0.10.0 includes both fixes. Older ClawMem versions (< v0.10.0) on OpenClaw v2026.4.11+ will fail to discover silently — upgrade ClawMem, then re-run `clawmem setup openclaw`. See [docs/guides/upgrading.md](docs/guides/upgrading.md#v090--v0100).\n\n**Alternative:** OpenClaw agents can also use ClawMem's MCP server directly (`clawmem setup mcp`), with or without hooks. This gives full access to all 33 MCP tools but bypasses OpenClaw's plugin lifecycle, so you lose token budget awareness, native compaction orchestration, and the `agent_end` message pipeline. The native OpenClaw plugin is recommended for new setups; MCP is available as an additional or standalone integration.\n\n#### Hermes Agent\n\nClawMem integrates as a native MemoryProvider plugin — Hermes's pluggable interface for agent memory. Same automatic retrieval and extraction, delivered through Hermes's memory lifecycle instead of Claude Code hooks.\n\n**Install:**\n\n```bash\n# Preferred — user-plugin path (Hermes #10529, v2026.4.13+).\n# Survives `git pull` of hermes-agent and avoids dual-registration with bundled providers.\n# Copies the directory's CONTENTS, so the same command installs and upgrades.\nmkdir -p \"${HERMES_HOME:-$HOME/.hermes}/plugins/clawmem\"\ncp -r /path/to/ClawMem/src/hermes/. \"${HERMES_HOME:-$HOME/.hermes}/plugins/clawmem/\"\n\n# Or, the bundled-style path (always supported, takes precedence on name collisions).\n# Recommended only when you actively work in the hermes-agent source tree.\nmkdir -p /path/to/hermes-agent/plugins/memory/clawmem\ncp -r /path/to/ClawMem/src/hermes/. /path/to/hermes-agent/plugins/memory/clawmem/\n\n# Symlink alternative for in-place development (either path).\nln -s /path/to/ClawMem/src/hermes ${HERMES_HOME:-~/.hermes}/plugins/clawmem\n```\n\n**Configure** in your Hermes profile's `.env` or environment:\n```bash\nCLAWMEM_BIN=/path/to/clawmem          # Path to clawmem binary (or ensure it's on PATH)\nCLAWMEM_SERVE_PORT=7438                # REST API port (default: 7438)\nCLAWMEM_SERVE_MODE=external            # \"external\" (you run clawmem serve) or \"managed\" (plugin manages it)\nCLAWMEM_PROFILE=balanced               # speed | balanced | deep\n```\n\nThen set `memory.provider: clawmem` in your Hermes `config.yaml`, or run `hermes memory setup` to configure interactively.\n\n**What the plugin provides:**\n\n- **`prefetch()`** — prompt-aware retrieval via `context-surfacing` hook (automatic every turn)\n- **`sync_turn()`** — appends the turn to the plugin's transcript, then runs decision extraction, handoff generation and the feedback loop over it in the background (v0.41.0: after every turn; each turn is processed once)\n- **`on_session_end()`** — a last pass, then the SessionEnd handoff flush\n- **`on_pre_compress()`** — pre-compaction state preservation\n- **`session-bootstrap`** — session registration + first-turn context injection\n- **5 agent tools** — `clawmem_retrieve`, `clawmem_get`, `clawmem_session_log`, `clawmem_timeline`, `clawmem_similar`\n- **Plugin-managed transcript** — maintains its own JSONL transcript for ClawMem hooks\n\n**Requirements:** `clawmem` binary on PATH and `clawmem serve` running (external mode) or the plugin starts it automatically (managed mode). Python 3.10+. No pip dependencies beyond Hermes itself (uses `urllib` for REST calls, `httpx` optional for better performance).\n\n**Alternative:** Hermes also has built-in MCP client support. You can add ClawMem as an MCP server in Hermes's `config.yaml` under `mcp_servers` for tool-only access. But this misses the lifecycle hooks (prefetch, session_end, pre_compress), so the native plugin is recommended.\n\nSee [Hermes plugin guide](docs/guides/hermes-plugin.md) for architecture details, lifecycle mapping, and troubleshooting.\n\n#### Multi-Framework Operation\n\nAll three integrations share the same SQLite vault by default. Claude Code, OpenClaw, and Hermes can run simultaneously — decisions captured in one runtime are immediately available in the others, giving agents persistent shared memory across sessions and platforms. WAL mode + busy_timeout handles concurrent access.\n\n#### Multi-Vault (Optional)\n\nBy default, ClawMem uses a single vault at `~/.cache/clawmem/index.sqlite`. For users who want separate memory domains (e.g., work vs personal, or isolated vaults per project), ClawMem supports named vaults.\n\n**Configure in `~/.config/clawmem/config.yaml`:**\n\n```yaml\nvaults:\n  work: ~/.cache/clawmem/work.sqlite\n  personal: ~/.cache/clawmem/personal.sqlite\n```\n\n**Or via environment variable:**\n\n```bash\nexport CLAWMEM_VAULTS='{\"work\":\"~/.cache/clawmem/work.sqlite\",\"personal\":\"~/.cache/clawmem/personal.sqlite\"}'\n```\n\n**Using vaults with MCP tools:**\n\nAll retrieval tools (`memory_retrieve`, `query`, `search`, `vsearch`, `intent_search`) accept an optional `vault` parameter. Omit it to use the default vault.\n\n```\n# Search the default vault (no vault param needed)\nquery(\"authentication flow\")\n\n# Search a named vault\nquery(\"project timeline\", vault=\"work\")\n\n# List configured vaults\nlist_vaults()\n\n# Sync content into a vault\nvault_sync(vault=\"work\", content_root=\"~/work/docs\")\n```\n\n**Single-vault users:** No action needed. Everything works without configuration. The `vault` parameter is always optional and ignored when no vaults are configured.\n\n### Inference services (GPU, in-process, or cloud)\n\nClawMem uses three inference services — **embedding**, **LLM** (query expansion / intent / A-MEM / the Stop hooks' observer), and **reranker**. In the **default** stack all three run as `llama-server` instances, each with an in-process `node-llama-cpp` fallback that auto-downloads on first use, so ClawMem works without a dedicated GPU (Metal on Apple Silicon, Vulkan where available, CPU as last resort). The `bin/clawmem` wrapper points at `localhost:8088/8089/8090`. **Always run via `bin/clawmem`** — it sets the endpoints.\n\n**Choose a stack:**\n\n| Stack | Models | VRAM | License | When |\n|---|---|---|---|---|\n| **QMD native** (default) | EmbeddingGemma-300M + qmd-query-expansion-1.7B + qwen3-reranker-0.6B | ~4 GB, or in-process | **Permissive — commercial OK** | Any GPU or none; zero-config start |\n| **z / SOTA** | zembed-1 + qmd-query-expansion-1.7B + zerank-2 (**Q8_0 GGUF** that carries its score head) | ~13 GB | **Apache-2.0 — commercial OK** | 16 GB+ GPU; best recall |\n| **Cloud embedding** | Jina / OpenAI / Voyage / Cohere (embedding only) | none | provider ToS | No local GPU for embedding; LLM + reranker stay local |\n\n**Heads-up before you serve:** most zerank-2 **GGUFs are inert** — llama.cpp's standard converter drops the score head. Serve the Q8_0 GGUF that carries it ([launch line](docs/guides/inference-services.md#sota-stack--z-models-16-gb-gpu-apache-20)) or the bf16 [seq-cls sidecar](extras/rerankers/zerank-2-seq/), and verify with `clawmem rerank-health`. zembed-1 / reranking need `-ub` = `-b` (non-causal attention). Changing embedding dimensions requires `clawmem embed --force`. Set `CLAWMEM_NO_LOCAL_MODELS=true` to fail fast instead of silent CPU fallback.\n\n→ **Full stack decision matrix, model/VRAM tables, and server-setup commands:** [docs/guides/inference-services.md](docs/guides/inference-services.md). Cloud providers, batch + TPM behavior: [docs/guides/cloud-embedding.md](docs/guides/cloud-embedding.md). All environment variables: [docs/reference/configuration.md](docs/reference/configuration.md). Keeping servers running: [docs/guides/systemd-services.md](docs/guides/systemd-services.md).\n\n### MCP Server\n\nClawMem exposes 33 MCP tools via the [Model Context Protocol](https://modelcontextprotocol.io) and an optional HTTP REST API. Any MCP-compatible client or HTTP client can use it.\n\n**Claude Code (automatic):**\n\n```bash\n./bin/clawmem setup mcp   # Registers in ~/.claude.json\n```\n\n**Manual (any MCP client):**\n\nAdd to your MCP config (e.g. `~/.claude.json`, `claude_desktop_config.json`, or your client's equivalent):\n\n```json\n{\n  \"mcpServers\": {\n    \"clawmem\": {\n      \"command\": \"/absolute/path/to/clawmem/bin/clawmem\",\n      \"args\": [\"mcp\"]\n    }\n  }\n}\n```\n\nThe server runs via stdio — no network port needed. The `bin/clawmem` wrapper sets the GPU endpoint env vars automatically.\n\n**Verify:** After registering, your client should see tools including `memory_retrieve`, `search`, `vsearch`, `query`, `query_plan`, `intent_search`, `timeline`, etc.\n\n### HTTP REST API (optional)\n\nFor web dashboards, non-MCP agents, cross-machine access, or programmatic use:\n\n```bash\n./bin/clawmem serve                          # localhost:7438, no auth\n./bin/clawmem serve --port 8080              # custom port\nCLAWMEM_API_TOKEN=secret ./bin/clawmem serve # with bearer token auth\n```\n\n**Endpoints:**\n\n| Method | Path | Description |\n|---|---|---|\n| GET | `/health` | Liveness probe + version + doc count |\n| GET | `/stats` | Full index statistics |\n| POST | `/search` | Unified search (`mode`: auto/keyword/semantic/hybrid) |\n| POST | `/retrieve` | Smart retrieve with auto-routing (`mode`: auto/keyword/semantic/causal/timeline/hybrid) |\n| GET | `/documents/:docid` | Single document by 6-char hash prefix |\n| GET | `/documents?pattern=...` | Multi-get by glob pattern |\n| GET | `/timeline/:docid` | Temporal neighborhood (before/after) |\n| GET | `/sessions` | Recent session history |\n| GET | `/collections` | List all collections |\n| GET | `/lifecycle/status` | Active/archived/forgotten/pinned/snoozed counts + `deactivation_reasons` (`absent`/`forget`/`archive`/`unknown_legacy`) |\n| POST | `/documents/:docid/pin` | Pin/unpin |\n| POST | `/documents/:docid/snooze` | Snooze until date |\n| POST | `/documents/:docid/forget` | Deactivate |\n| POST | `/lifecycle/sweep` | Archive stale docs (dry_run default) |\n| GET | `/graph/causal/:docid` | Causal chain traversal |\n| GET | `/graph/similar/:docid` | k-NN neighbors |\n| GET | `/export` | Active-document export as JSON (`?full=true` includes legacy `precompact-state.md` snapshot copies) |\n| POST | `/reindex` | Trigger re-scan |\n| POST | `/graphs/build` | Rebuild temporal + semantic graphs |\n\n**Auth:** Set `CLAWMEM_API_TOKEN` env var to require `Authorization: Bearer <token>` on all requests. If unset, access is open (localhost-only by default). See `.env.example`.\n\n**Search example:**\n\n```bash\ncurl -X POST http://localhost:7438/search \\\n  -H 'Content-Type: application/json' \\\n  -d '{\"query\": \"authentication decisions\", \"mode\": \"hybrid\", \"compact\": true}'\n```\n\n### Verify Installation\n\n```bash\n./bin/clawmem doctor   # Full health check\n./bin/clawmem status   # Quick index status\nbun test               # Run test suite (from the repository root)\n```\n\n## Agent Instructions\n\nClawMem ships agent instruction files and an optional maintenance agent:\n\n| File | Loaded | Purpose |\n|------|--------|---------|\n| `AGENTS.md` | Automatically (most agents, when working in this repo) | **Lean root SSOT** — agent-facing quick reference (inference at a glance, install, retrieval routing, MCP tools, indexing rules, integrations) + an index into `docs/` |\n| `CLAUDE.md` | Automatically (Claude Code) | `@AGENTS.md` import — Claude Code reads `CLAUDE.md` natively, so it just pulls in the SSOT |\n| `SKILL.md` | On-demand (agent reads when needed) | Portable operating reference — escalation gate, tool routing, the 4 query-optimization levers, pipeline behavior, composite scoring, lifecycle. Shipped with the package for cross-project use |\n| `docs/` | On-demand (linked throughout `AGENTS.md`) | Deep reference — inference setup, configuration, concepts, internals, guides, troubleshooting |\n| `agents/clawmem-curator.md` | On-demand via `clawmem setup curator` | Maintenance agent — lifecycle triage, retrieval health checks, dedup sweeps, graph rebuilds |\n\n**Working in the ClawMem repo:** No action needed — `CLAUDE.md` (which imports `AGENTS.md`) loads automatically.\n\n**Using ClawMem from other projects:** Your agent needs instructions on how to use ClawMem's hooks and MCP tools. Two options:\n\n### Option A: Copy instructions into your project\n\nCopy the contents of `AGENTS.md` (or the relevant sections) into your project's own `AGENTS.md` or `CLAUDE.md`. Simple but requires manual updates when ClawMem changes.\n\n### Option B: Add a trigger block (recommended)\n\nAdd this minimal trigger block to your global `~/.claude/CLAUDE.md`. It gives the agent routing rules always loaded, and tells it how to find the full reference (SKILL.md) shipped with your installation when deeper guidance is needed:\n\n```markdown\n## ClawMem\n\nArchitecture: hooks (automatic, ~90%) + MCP tools (explicit, ~10%).\n\nVault: `~/.cache/clawmem/index.sqlite` | Config: `~/.config/clawmem/config.yaml`\n\n### Escalation Gate (3 rules — ONLY escalate to MCP tools when one fires)\n\n1. **Low-specificity injection** — `<vault-context>` is empty or lacks the specific fact needed\n2. **Cross-session question** — \"why did we decide X\", \"what changed since last time\"\n3. **Pre-irreversible check** — before destructive or hard-to-reverse changes\n\n### Tool Routing (once escalated)\n\n**Preferred:** `memory_retrieve(query)` — auto-classifies and routes to the optimal backend.\n\n**Direct routing** (when calling specific tools):\n\n    \"why did we decide X\"         → intent_search(query)          NOT query()\n    \"what happened last session\"  → session_log()                 NOT query()\n    \"what else relates to X\"      → find_similar(file)            NOT query()\n    Complex multi-topic           → query_plan(query)             NOT query()\n    General recall                → query(query, compact=true)\n    Keyword spot check            → search(query, compact=true)\n    Conceptual/fuzzy              → vsearch(query, compact=true)\n    Full content                  → multi_get(\"path1,path2\")\n    Lifecycle health              → lifecycle_status()\n    Stale sweep                   → lifecycle_sweep(dry_run=true)\n    Restore archived              → lifecycle_restore(query)\n\nALWAYS `compact=true` first → review → `multi_get` for full content.\n\n### Proactive Use (no escalation gate needed)\n\n- User says \"remember this\" / critical decision made → `memory_pin(query)` immediately\n- User corrects a misconception → `memory_pin(query)` the correction\n- `<vault-context>` surfaces irrelevant/noisy content → `memory_snooze(query, until)` for 30 days\n- Need to correct a memory → `memory_forget(query)`\n- After bulk ingestion → `build_graphs`\n\n### Anti-Patterns\n\n- Do NOT use `query()` for everything — match query type to tool, or use `memory_retrieve`\n- Do NOT call query/intent_search every turn — 3 rules above are the only gates\n- Do NOT re-search what's already in `<vault-context>`\n- Do NOT pin everything — pin is for persistent high-priority items, not routine decisions\n- Do NOT forget memories to \"clean up\" — let confidence decay handle it\n- Do NOT wait for curator to pin decisions — pin immediately when critical\n\nFor detailed operating guidance (escalation gate, tool routing, query-optimization levers, pipeline behavior, composite scoring, lifecycle), find and read the shipped SKILL.md (setup, inference, and internals live in AGENTS.md + docs/):\n  Bash: CLAWMEM_ROOT=$(cd \"$(dirname \"$(which clawmem)\")/..\" && pwd) && echo \"$CLAWMEM_ROOT/SKILL.md\"\n  Then: Read the file at that path.\n```\n\nThis gives your agent the 3-rule gate, tool routing, and proactive behaviors always loaded. When it needs deeper guidance, it locates and reads the full SKILL.md reference shipped with your installation — no symlinks or skill registration required.\n\n---\n\n## CLI Reference\n\n```\nclawmem init                                    Create DB + config\nclawmem bootstrap <vault> [--name N] [--skip-embed]  One-command setup\nclawmem collection add <path> --name <name>     Add a collection\nclawmem collection list                         List collections\nclawmem collection remove <name>                Remove a collection\n\nclawmem update [--pull] [--embed]               Incremental re-scan\nclawmem mine <dir> [-c name] [--embed] [--synthesize]  Import conversation exports (--synthesize runs post-import LLM fact extraction, v0.7.2; preserves per-exchange authored_at, v0.27.0)\nclawmem mine <dir> -c name --backfill-dates [--apply]  Derive authored_at for already-mined docs (metadata-only; dry-run without --apply)\nclawmem embed [-f]                              Generate fragment embeddings\nclawmem reindex [--force]                       Full re-index\nclawmem watch                                   File watcher daemon\n\nclawmem search <query> [-n N] [--json]          BM25 keyword search\nclawmem vsearch <query> [-n N] [--json]         Vector semantic search\nclawmem query <query> [-n N] [--json]           Full hybrid pipeline\n\nclawmem profile                                 Show user profile\nclawmem profile rebuild                         Force profile rebuild\nclawmem update-context                          Regenerate per-folder CLAUDE.md\n\nclawmem list [-n/--limit N] [-c col] [--json]   Browse recent documents\nclawmem budget [--session ID]                   Token utilization\nclawmem log [--last N]                          Session history\nclawmem hook <name>                             Manual hook trigger\nclawmem surface --context --stdin               IO6: pre-prompt context injection\nclawmem surface --bootstrap --stdin             IO6: per-session bootstrap injection\n\nclawmem reflect [N]                             Cross-session reflection (last N days, default 14)\nclawmem consolidate [--dry-run] [N]             Find and archive duplicate low-confidence docs\nclawmem eval run --gold <file.jsonl>            Offline eval: replay gold-labeled queries, score J_doc/recall/MRR\n\nclawmem install-service [--enable] [--remove]   Systemd watcher service\nclawmem setup hooks [--remove]                  Install/remove Claude Code hooks\nclawmem setup mcp [--remove]                    Register/remove MCP server\nclawmem setup curator [--remove]                Install/remove curator maintenance agent\nclawmem mcp                                     Start stdio MCP server\nclawmem serve [--port 7438] [--host 127.0.0.1]  Start HTTP REST API server\nclawmem path                                    Print database path\nclawmem doctor                                  Full health check\nclawmem status                                  Quick index status\n```\n\n## MCP Tools (31)\n\nRegistered by `clawmem setup mcp`. Available to any MCP-compatible client.\n\n**Internal-collection visibility (v0.21.0):** the retrieval tools `search`, `vsearch`, `query`, `query_plan`, `memory_retrieve`, and `find_similar` (plus `memory_rank` since v0.36.0) exclude the system-internal `_clawmem` collection by default — pass `includeInternal: true` (or name `_clawmem` in an explicit `collection` filter where the tool has one) to include it. `find_similar` auto-includes internal neighbors when the reference document is itself internal; `intent_search`, `find_causal_links`, `kg_query`, `session_log`, and `timeline` are unfiltered by design. Full contract (including the `degraded` under-fill markers): [docs/reference/mcp-tools.md](docs/reference/mcp-tools.md).\n\n| Tool | Description |\n|---|---|\n| `__IMPORTANT` | Workflow guide: prefer `memory_retrieve` → match query type to tool → `multi_get` for full content |\n\n### Core Search & Retrieval\n\n| Tool | Description |\n|---|---|\n| `memory_retrieve` | **Preferred entry point.** Auto-classifies query and routes to optimal backend (query, intent_search, session_log, find_similar, or query_plan). Use instead of manually choosing a search tool. |\n| `search` | BM25 keyword search — for exact terms, config names, error codes, filenames. **v0.24.0: non-recency queries rank by the RAW BM25 transform** (`scoreBasis: \"fts-bm25\"`; judged keyword eval MRR 0.848 vs composite 0.415; metadata breaks exact ties only; `minScore` filters raw, no default); recency-intent queries keep composite. Collection filter supports comma-separated values. Prefer `memory_retrieve` for auto-routing. |\n| `vsearch` | Vector semantic search — for conceptual/fuzzy matching when exact keywords are unknown. **v0.22.0: non-recency queries rank by RAW cosine (`scoreBasis: \"vector-cosine\"`; metadata breaks exact ties only; `minScore` filters raw with no default)**; recency-intent queries keep composite. Collection filter supports comma-separated values. Prefer `memory_retrieve` for auto-routing. |\n| `query` | Full hybrid pipeline (BM25 + vector + rerank) — general-purpose when query type is unclear. WRONG for \"why\" questions (use `intent_search`) or cross-session queries (use `session_log`). Prefer `memory_retrieve` for auto-routing. Intent hint, strong-signal bypass, chunk dedup, candidateLimit, MMR diversity, compact mode. |\n| `get` | Retrieve single document by path or docid |\n| `multi_get` | Retrieve multiple docs by glob or comma-separated list |\n| `find_similar` | USE THIS for \"what else relates to X\", \"show me similar docs\". Finds k-NN vector neighbors — discovers connections beyond keyword overlap that search/query cannot find. |\n\n### Intent-Aware Search\n\n| Tool | Description |\n|---|---|\n| `intent_search` | USE THIS for \"why did we decide X\", \"what caused Y\", \"who worked on Z\". Classifies intent (WHY/WHEN/ENTITY/WHAT), traverses causal + semantic graph edges. Returns decision chains that `query()` cannot find. |\n| `query_plan` | USE THIS for complex multi-topic queries (\"tell me about X and also Y\", \"compare A with B\"). Decomposes into parallel typed clauses (bm25/vector/graph), executes each, merges via RRF. `query()` searches as one blob — this tool splits topics and routes each optimally. |\n\n**`intent_search` pipeline:** Query → Intent Classification → BM25 + Vector → Intent-Weighted RRF → Graph Expansion (WHY/ENTITY intents) → Cross-Encoder Reranking → Composite Scoring\n\n**`query_plan` pipeline:** Query → LLM decomposition into 2-4 typed clauses → Parallel execution (BM25/vector/graph per clause) → RRF merge across clauses → Composite scoring. Falls back to single-query for simple inputs.\n\n### Multi-Graph & Causal\n\n| Tool | Description |\n|---|---|\n| `build_graphs` | Build temporal and/or semantic graphs from document corpus |\n| `find_causal_links` | Trace decision chains: \"what led to X\", \"how we got from A to B\". Follow up `intent_search` with this tool on a top result to walk the full causal chain. Traverses causes / caused_by / both up to N hops with depth-annotated reasoning. |\n| `kg_query` | Query the SPO knowledge graph: \"what does X relate to?\", \"what was true about X when?\". Returns temporal entity-relationship triples with validity windows. Accepts entity name (resolved via `searchEntities`) or canonical ID in `vault:type:slug` form. Triples are populated by the decision-extractor hook from observer-emitted `<triples>` blocks. |\n| `memory_evolution_status` | Show how a document's A-MEM metadata evolved over time |\n| `timeline` | Show the temporal neighborhood around a document — what was created/modified before and after it. Progressive disclosure: search → timeline (context) → get (full content). Supports same-collection scoping and session correlation. |\n\n### Beads Integration\n\n| Tool | Description |\n|---|---|\n| `beads_sync` | Sync Beads issues from Dolt backend (`bd` CLI) into memory: syncs the full backlog (no 50-issue cap), creates docs, bridges all dep types to `memory_relations`, surfaces bd ≥1.1.0 claim leases, runs A-MEM enrichment |\n\n### Vault Management\n\n| Tool | Description |\n|---|---|\n| `list_vaults` | Show configured vault names and paths. Empty in single-vault mode. |\n| `vault_sync` | Index markdown from a directory into a named vault. Restricted-path validation rejects sensitive directories. |\n\n### Agent Diary\n\n| Tool | Description |\n|---|---|\n| `diary_write` | Write a diary entry. Use for recording important events, decisions, or observations in environments without hook support. Stored as searchable memories. |\n| `diary_read` | Read recent diary entries. Filter by agent name. |\n\n### Memory Management & Lifecycle\n\n| Tool | Description |\n|---|---|\n| `memory_forget` | Search → deactivate closest match (with audit trail). Weak matches return a disambiguation list instead of acting (v0.23.0) |\n| `memory_pin` | Pin a memory: lifecycle retention + priority among relevance-equivalent results (+0.3 composite boost on hook/`query` surfaces; exact-tie precedence on the raw routes — vector + `search` non-recency). USE PROACTIVELY when: user states a persistent constraint, makes an architecture decision, or corrects a misconception. Don't wait for curator — pin critical decisions immediately. |\n| `memory_snooze` | Temporarily hide a memory from context surfacing until a date. USE PROACTIVELY when `<vault-context>` repeatedly surfaces irrelevant content — snooze for 30 days instead of ignoring it. |\n| `status` | Index health with content type distribution |\n| `reindex` | Trigger vault re-scan |\n| `index_stats` | Detailed stats: types, staleness, access counts, sessions |\n| `memory_stats` | Lifecycle + ranking-metadata aggregates per collection (v0.36.0): origin×active cross-tabs, pinned, accrual, deactivation reasons, and access/confidence/quality/effective-age distributions (mean/median/min/max over active rows). Deeper than `index_stats`; includes system collections. |\n| `memory_rank` | Ranking diagnostic (v0.36.0): real-pipeline composite breakdown per result — weights, recency, confidence blend, quality/length/frequency/canonical multipliers, signed pinΔ, co-activation — plus raw-vs-composite rank shifts; demoted raw winners stay visible. FTS-only candidates; read-only. |\n| `session_log` | USE THIS for \"last time\", \"yesterday\", \"what happened\", \"what did we do\". Returns session history with handoffs and file changes. DO NOT use `query()` for cross-session questions — this tool has session-specific data that search cannot find. |\n| `profile` | Current static + dynamic user profile |\n| `lifecycle_status` | Document lifecycle statistics: active, archived, forgotten, pinned, snoozed counts, the deactivation-reason breakdown, and policy summary |\n| `lifecycle_sweep` | Run lifecycle policies: archive stale docs past retention threshold. Archives only — never deletes. Defaults to dry_run (preview only) |\n| `lifecycle_restore` | Restore documents that were auto-archived by lifecycle policies. Filter by query, collection, or restore all |\n\n**ClawMem never physically deletes a document row (v0.30.0).** Forget and archive deactivate; `lifecycle_restore` reverses archival; `purge_after_days` is inert. Through v0.29.0 a configured retention window permanently deleted archived rows from a non-dry-run sweep and from the SessionStart hook, without reporting it — see [upgrading](docs/guides/upgrading.md#v0300-clawmem-no-longer-deletes-document-rows).\n\n### Compact Mode\n\n`search`, `vsearch`, and `query` accept `compact: true` to return `{ id, path, title, score, snippet, content_type, fragment }` instead of full content. Saves ~5x tokens for initial filtering.\n\n## Hooks (Claude Code Integration)\n\nHooks installed by `clawmem setup hooks`:\n\n| Hook | Event | What It Does |\n|---|---|---|\n| `context-surfacing` | UserPromptSubmit | Retrieval gate → lane-based hybrid search (BM25 + vector + file-aware (E13) + gated prior-turn + deep expansion variants) → weighted RRF fusion onto one channel-aware ordering key → snooze/noise filters → relevance admission with query-level abstention (v0.38.0) → tiered injection (HOT/WARM/COLD) → `<vault-context>` + `<vault-routing>` hint. Profile-driven budget/results/timeout; `CLAWMEM_HOOK_BUDGET_MS` is the authoritative internal deadline. |\n| `postcompact-inject` | SessionStart (compact) | Re-injects context after compaction, framed as reference data: this session's pre-compaction state + recent decisions + antipatterns + vault context (1200 token budget) |\n| `curator-nudge` | SessionStart | Surfaces curator report actions, nudges when report is stale (>7 days) |\n| `precompact-extract` | PreCompact | Extracts the last typed request, decisions, file paths and open questions before compaction → the vault's session-keyed `compaction_state` row, taken once by the same session's `postcompact-inject` |\n| `decision-extractor` | Stop | GGUF observer extracts structured observations (decisions, preferences, milestones, problems, bugfixes, features, refactors, discoveries) from the turns after its per-transcript cursor, each turn once (v0.41.0), into the session's own decision and antipattern docs; detects contradictions with prior decisions (judge-gated — requires `CLAWMEM_JUDGE_*`, v0.29.0) |\n| `handoff-generator` | Stop | Digests each new turn without a model, then folds the digests into an incremental, throttled observer summary → the session's handoff |\n| `handoff-generator` | SessionEnd | Renders the handoff's latest turns at session end (no transcript read, no model; v0.41.0) |\n| `feedback-loop` | Stop | Silently credits each surfaced note once per turn when that turn verifiably names it (path, file name or rendered title): access count, co-activation + usage relations among the notes that turn referenced, utility signals (surfaced vs referenced ratio for lifecycle automation) |\n\nAdditional hooks available but not installed by default:\n\n| Hook | Event | Why Not Default |\n|---|---|---|\n| `session-bootstrap` | SessionStart | Injects ~2000 tokens before user types anything. `context-surfacing` on first prompt is more precise. |\n| `staleness-check` | SessionStart | Redundant without `session-bootstrap` (stale notes are part of its output). |\n| `pretool-inject` | PreToolUse | Disabled in HOOK_EVENT_MAP (cannot inject additionalContext via PreToolUse). |\n\nHooks handle ~90% of retrieval automatically. For agent escalation logic (when to use MCP tools vs rely on hooks), see `CLAUDE.md`.\n\n## Search Pipeline\n\n```\nUser Query + optional intent hint\n  → BM25 Probe → Strong Signal Check (skip expansion if top hit ≥ 0.85 with gap ≥ 0.15; disabled when intent provided)\n  → Query Expansion (intent steers LLM prompt when provided)\n  → BM25 + Vector Search (parallel, original query 2× weight)\n  → Reciprocal Rank Fusion → slice to candidateLimit (default 30)\n  → Intent-Aware Chunk Selection (intent terms at 0.5× weight alongside query terms at 1.0×)\n  → Cross-Encoder Reranking (4000 char context; intent prepended; chunk dedup; batch cap=4)\n  → Rerank/RRF Blend (blendRerank: 0.9·reranker + 0.1·normalized-RRF tiebreaker; reranker can promote over RRF #1; falls back to RRF order if reranker unavailable)\n  → Composite Scoring (query-tuned: (search × 0.70 + recency × 0.15 + confidence × 0.15) × qualityMultiplier × lengthNorm × coActivationBoost + pinBoost; recency-intent queries → 0.10/0.70/0.20; other tools keep the 0.50/0.25/0.25 default)\n  → MMR Diversity Filter (Jaccard bigram similarity > 0.6 → demoted)\n  → Ranked Results\n```\n\nFor agent-facing query optimization (tool selection, query string quality, intent parameter, candidateLimit), see `CLAUDE.md`.\n\n### Multi-Graph Traversal\n\nFor WHY and ENTITY queries, the search pipeline expands results through the memory graph:\n\n1. Start from top-10 baseline results as anchor nodes\n2. For each frontier node: get neighbors via any relation type\n3. Score transitions: `λ1·structure + λ2·semantic_affinity`\n4. Apply decay: `new_score = parent_score * γ + transition_score`\n5. Keep top-k (beam search), repeat until max depth or budget\n\n**Graph types:**\n- **Semantic** — vector similarity edges (threshold > 0.7)\n- **Temporal** — chronological document ordering\n- **Causal** — LLM-inferred cause→effect from Observer facts + Beads `blocks`/`waits-for` deps\n- **Supporting** — LLM-analyzed document relationships + Beads `discovered-from` deps\n- **Contradicts** — LLM-analyzed document relationships. Additional `contradicts` edges are inserted by Phase 3 deductive synthesis when a new draft contradicts a prior deductive observation. *(Phase 2's merge-time gate does not insert edges — a blocked merge under `link` sets the old consolidated row's `invalidated_by` backlink instead.)*\n\n### Content Type Scoring\n\n| Type | Half-life | Baseline | Notes |\n|---|---|---|---|\n| `decision` | 180d | 0.85 | Very slow ranking decay (§36.11) — silently-abandoned decisions stop winning ranking; attention-decay-exempt; lifecycle policy separate |\n| `deductive` | ∞ | 0.85 | Never decays — cross-session derived insights with source provenance |\n| `preference` | ∞ | 0.80 | Never decays — user preferences are durable facts |\n| `hub` | ∞ | 0.80 | Never decays |\n| `antipattern` | ∞ | 0.75 | Never decays — accumulated negative patterns persist |\n| `problem` | 60 days | 0.75 | High priority but resolves over time |\n| `research` | 90 days | 0.70 | |\n| `milestone` | 60 days | 0.70 | Important at the time, fades as project moves forward |\n| `project` | 120 days | 0.65 | |\n| `handoff` | 30 days | 0.60 | Fast decay — most recent matters |\n| `conversation` | 45 days | 0.55 | Imported chat exchanges |\n| `progress` | 45 days | 0.50 | |\n| `note` | 60 days | 0.50 | Default |\n\nContent types are inferred from frontmatter or file path patterns. Half-lives extend up to 3× for frequently-accessed memories (access reinforcement, decays over 90 days). Non-durable types (handoff, progress, conversation, note, project) lose 5% confidence per week without access (attention decay). Decision/deductive/preference/hub/research/antipattern are exempt.\n\n**Quality scoring:** Each document gets a `quality_score` (0.0–1.0) computed during indexing based on length, structure (headings, lists), decision/correction keywords, and frontmatter richness. Applied as `qualityMultiplier = 0.7 + 0.6 × qualityScore` (range: 0.7× penalty to 1.3× boost).\n\n**Length normalization:** `1/(1 + 0.5 × log2(max(bodyLength/500, 1)))` — penalizes verbose entries that dominate via keyword density. Floor at 30% of original score.\n\n**Frequency boost:** Documents with higher revision counts or duplicate counts get a durability signal: `freqSignal = (revisions - 1) × 2 + (duplicates - 1)`, `freqBoost = min(0.10, log1p(freqSignal) × 0.03)`. Revision count (content evolution) is weighted 2× vs duplicate count (ingest repetition). Capped at 10%.\n\n**Pin boost:** Pin = lifecycle retention + priority among relevance-equivalent results. On composite surfaces pinned documents get a +0.3 additive boost (capped at 1.0); on the raw routes — the vector tools (v0.22.0) and non-recency `search` (v0.24.0) — pin breaks exact raw-score ties only. Use `memory_pin` to pin critical memories.\n\n**Snooze:** Snoozed documents are filtered out of context surfacing until their snooze date. Use `memory_snooze` for temporary suppression.\n\n**Contradiction detection (judge-gated, v0.29.0):** Contradiction analysis runs only when a **judge** is configured via `CLAWMEM_JUDGE_*` — without one it is disabled as an audited no-op, because the stock expansion model cannot meet the judge contract ([details](docs/guides/inference-services.md#contradiction-judge)). With a judge: when `decision-extractor` identifies a new decision that contradicts a prior one, the old decision's confidence is automatically lowered (−0.25 for contradictions, −0.15 for updates). Superseded decisions naturally fade from context surfacing without manual intervention. When erosion reaches the `0.2` floor the hook can additionally set `invalidated_at`, which removes the document from FTS and vector retrieval entirely. That step applies **only to `content_type='observation'` rows** — a superseded *decision* is eroded but never retired — and is **off by default** behind `CLAWMEM_CONTRADICTION_INVALIDATE` and logs `WOULD invalidate` instead of writing, because its exposure depends on the vault's confidence distribution and content-type mix ([calibration guide](docs/guides/contradiction-invalidation.md)). *Two contract defects fixed in v0.28.0 had previously prevented this path from applying any classification at all — earlier versions classified but never mutated a document.* **v0.7.1 adds a second layer at the consolidation boundary:** before the background worker merges a new pattern into an existing consolidated observation, a deterministic heuristic (negation asymmetry, number/date mismatch) plus the configured judge detect contradictions (heuristic-only, and constrained to `link`, when no judge is configured). Blocked merges route to either `link` policy (both rows remain active; the old row gains an `invalidated_by` backlink, default) or `supersede` policy (old row marked `status='inactive'` — requires a configured judge, otherwise loudly constrained to `link`). Configurable via `CLAWMEM_CONTRADICTION_POLICY` and `CLAWMEM_CONTRADICTION_MIN_CONFIDENCE`. Mutation-authorizing evaluations commit their durable `judge_runs`/`judge_events` audit rows in the same transaction as the mutation (Phase-3 deductive checks commit a precondition audit first; non-mutating outcomes write standalone rows) — that audit is what calibration reads. Data-egress note: a cloud or subscription judge receives the new decisions and the retrieved candidate snippets.\n\n## Features\n\n### A-MEM (Adaptive Memory Evolution)\n\nDocuments are automatically enriched with structured metadata when indexed:\n- **Keywords** (3-7 specific terms)\n- **Tags** (3-5 broad categories)\n- **Context** (1-2 sentence description)\n\nWhen new documents create links, neighboring documents' metadata evolves — keywords merge, context updates, and the evolution history is tracked with version numbers and reasoning.\n\n### Causal Inference\n\nThe decision-extractor hook analyzes Observer facts for causal relationships. When multiple facts exist in an observation, an LLM identifies cause→effect pairs (confidence ≥ 0.6). Causal chains can be queried via `find_causal_links` with multi-hop traversal using recursive CTEs.\n\n### Beads Integration\n\nProjects using [Beads](https://github.com/steveyegge/beads) (v0.58.0+, Dolt backend) issue tracking are fully integrated into the MAGMA memory graph:\n\n- **Auto-sync**: Watcher detects `.beads/` directory changes → `syncBeadsIssues()` queries `bd` CLI for live Dolt data → creates markdown docs in `beads` collection\n- **Dependency bridging**: All Beads dependency types map to `memory_relations` edges — `blocks`/`conditional-blocks`/`waits-for`/`caused-by`→causal, `discovered-from`/`supersedes`/`duplicates`→supporting, `relates-to`/`related`/`parent-child`→semantic. Tagged `{origin: \"beads\"}` for traceability.\n- **A-MEM enrichment**: New beads docs get full `postIndexEnrich()` — memory note construction, semantic/entity link generation, memory evolution\n- **Graph traversal**: `intent_search` and `find_causal_links` traverse beads dependency edges alongside observation-inferred causal chains\n- **Requirement**: `bd` binary on PATH or at `~/go/bin/bd`\n\n`beads_sync` MCP tool for manual sync; watcher handles routine operations automatically.\n\n### Fragment-Level Embedding\n\nDocuments are split into semantic fragments (sections, lists, code blocks, frontmatter, facts) and each fragment gets its own vector embedding. Full-doc embedding is preserved for broad-match queries.\n\n### Local Observer Agent\n\nUses the LLM server (shared with query expansion and intent classification) to extract structured observations from session transcripts. Observation types: `decision`, `bugfix`, `feature`, `refactor`, `discovery`, `change`, `preference`, `milestone`, `problem`. Each observation includes title, facts, narrative, concepts, and files read/modified. Preferences, milestones, and problems get first-class content_type treatment with dedicated confidence baselines and half-lives instead of being flattened to generic \"observation\". Regex patterns find decisions and antipatterns beside the model. A batch the model cannot answer (unavailable, or refusing the request) is quarantined and replayed later, never committed as empty; its regex finds are committed when the replay succeeds (v0.41.0). Each prompt is fitted in tokens to the LLM server's own context, with room kept for the reply, and a turn too long for one prompt runs as checkpointed windows that resume after a timeout (v0.41.2). Serve the observer with `-c 8192`; [inference services](docs/guides/inference-services.md#llm-server) covers the server's context size.\n\n### Recall Tracking\n\nEmpirical tracking of which documents are surfaced by retrieval, which queries surfaced them, and whether the assistant actually cited them. Provides signals beyond raw search relevance for lifecycle decisions:\n\n- **Per-query diversity**: docs surfaced by multiple distinct queries have proven cross-domain relevance\n- **Multi-day spacing**: docs surfaced across separate calendar days (spaced frequency) are more valuable than binge recalls in one session\n- **Negative signals**: docs surfaced frequently but rarely referenced are noise candidates for snooze\n- **Per-turn attribution**: feedback-loop pairs each transcript turn with the context-surfacing row that served it (prompt hash + the host's order of events, never position) and tests only that turn's answer against that turn's injected documents (v0.41.0)\n\nData feeds `lifecycle_status` (pin/snooze candidate reports) and `lifecycle_sweep` (recall-based recommendations). Adapted from [OpenClaw](https://github.com/openclaw/openclaw) dreaming promotion patterns.\n\n### User Profile\n\nTwo-tier auto-curated profile extracted from your decisions and hub documents:\n- **Static**: persistent facts (Levenshtein-deduplicated)\n- **Dynamic**: recent session context\n\nInjected at session start for instant personalization.\n\n### Prompt Injection Filtering\n\nFive detection layers protect injected content: legacy string patterns, role injection regex, instruction override patterns, delimiter injection, and unicode obfuscation detection. Filtered results are skipped entirely (no placeholder tokens wasted).\n\n### Consolidation Worker\n\nOptional background process that enriches documents missing A-MEM metadata. Runs on a configurable interval, processing 3 documents per tick. Non-blocking (Timer.unref).\n\n### Per-Folder CLAUDE.md Generation\n\nAutomatically generates context sections in per-folder CLAUDE.md files from recent decisions and session activity related to that directory.\n\n### Feedback Loop\n\nA surfaced note gets `access_count + 1` when a turn it was injected into names it — once per turn, when the turn is over (v0.41.0; earlier versions counted the whole session again at every Stop). Unreferenced notes decay via recency. Over time, useful notes rise and noise fades.\n\n### Offline Eval Harness\n\n`clawmem eval run --gold <file.jsonl>` replays hand-labeled queries through the real `query` tool handler and scores the retrieved documents against gold evidence: doc-level Jaccard (`|C∩E|/|C∪E|`), precision/recall@k, hit@k, MRR. Touches no retrieval, lifecycle, or telemetry state (normal inference caches may populate, as in any live query); writes `run.json` + `report.md` for A/B comparison between checkouts or DB snapshots. Gold schema, trust gates, and labeling discipline: [docs/guides/eval-harness.md](docs/guides/eval-harness.md).\n\n## Feature Flags\n\n| Variable | Default | Effect |\n|---|---|---|\n| `CLAWMEM_ENABLE_AMEM` | enabled | A-MEM note construction + link generation during indexing |\n| `CLAWMEM_ENABLE_CONSOLIDATION` | disabled | Background worker for backlog A-MEM enrichment |\n| `CLAWMEM_CONSOLIDATION_INTERVAL` | 300000 | Worker interval in ms (min 15000) |\n| `CLAWMEM_EMBED_URL` | `http://localhost:8088` | Embedding server URL. Uses llama-server (GPU or CPU) or cloud API. Falls back to in-process `node-llama-cpp` if unset. |\n| `CLAWMEM_EMBED_API_KEY` | (none) | API key for cloud embedding. Enables cloud mode: batch embedding, provider-specific params, TPM-aware pacing. |\n| `CLAWMEM_EMBED_MODEL` | `embedding` | Model name for embedding requests. Override for cloud providers (e.g. `jina-embeddings-v5-text-small`). |\n| `CLAWMEM_EMBED_TPM_LIMIT` | `100000` | Tokens-per-minute limit for cloud embedding pacing. Match to your provider tier. |\n| `CLAWMEM_EMBED_DIMENSIONS` | (none) | Output dimensions for OpenAI `text-embedding-3-*` Matryoshka models (e.g. `512`, `1024`). |\n| `CLAWMEM_LLM_URL` | `http://localhost:8089` | LLM server URL for intent/query/A-MEM and the Stop hooks' observer. Without it, falls to `node-llama-cpp` (if allowed). |\n| `CLAWMEM_LLM_API_KEY` | (none) | Bearer token for an authenticated remote LLM endpoint. Independent of the embed and rerank keys. |\n| `CLAWMEM_LLM_MODEL` | `qwen3` | Model name sent to the configured LLM endpoint. Override this for OpenAI-compatible proxies such as `gpt-5.4-mini`. |\n| `CLAWMEM_LLM_REASONING_EFFORT` | (none) | Optional top-level `reasoning_effort` field for Chat Completions endpoints that support it (for example OpenAI reasoning models). Leave unset for llama-server/vLLM unless your serving stack explicitly accepts that field. |\n| `CLAWMEM_LLM_NO_THINK` | `true` | Append `/no_think` to remote LLM prompts. Set to `fal","readmeFilename":"README.md"}