{"_id":"@claude-flow/neural","_rev":"22-bcfbef2c370f1121ed594a52ea179748","name":"@claude-flow/neural","dist-tags":{"v3alpha":"3.0.1","alpha":"3.0.1","latest":"3.1.1"},"versions":{"3.0.0-alpha.1":{"name":"@claude-flow/neural","version":"3.0.0-alpha.1","_id":"@claude-flow/neural@3.0.0-alpha.1","maintainers":[{"name":"ruvnet","email":"ruv@ruv.net"}],"dist":{"shasum":"472e808119a15edccb9a2ab9597651fc8430ceeb","tarball":"https://registry.npmjs.org/@claude-flow/neural/-/neural-3.0.0-alpha.1.tgz","fileCount":223,"integrity":"sha512-Qco1DeXa+2FGFEWWQvY6x2iUQWaHJbSGCLUKaqROyeFWZmcRYL7oO3ZmwGkdhyRMxV9fMt1mYPaV9buv1vHHRw==","signatures":[{"sig":"MEUCIQC7iDtsafPUN2HlnfENF+zW05G4+Trq9rwk1W+qQK5NnAIgCRTebGb3hWGhqR4xWycNN6uHtKGYzzQcVEOZcQ4D7p0=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":1692897},"main":"dist/index.js","type":"module","types":"dist/index.d.ts","exports":{".":"./dist/index.js"},"gitHead":"eddd37df1857aa406d944f35a110323012f169a3","scripts":{"test":"vitest run","build":"tsc"},"_npmUser":{"name":"ruvnet","email":"ruv@ruv.net"},"_npmVersion":"10.9.4","description":"Neural module - SONA learning integration, neural modes","directories":{},"_nodeVersion":"22.21.1","dependencies":{"@ruvector/sona":"latest","@claude-flow/memory":"^3.0.0-alpha.1"},"publishConfig":{"tag":"v3alpha","access":"public"},"_hasShrinkwrap":false,"_npmOperationalInternal":{"tmp":"tmp/neural_3.0.0-alpha.1_1767735888930_0.6534149477047189","host":"s3://npm-registry-packages-npm-production"}},"3.0.0-alpha.2":{"name":"@claude-flow/neural","version":"3.0.0-alpha.2","_id":"@claude-flow/neural@3.0.0-alpha.2","maintainers":[{"name":"ruvnet","email":"ruv@ruv.net"}],"dist":{"shasum":"85f71324f2167e5b1d8104ea014fd6346306593c","tarball":"https://registry.npmjs.org/@claude-flow/neural/-/neural-3.0.0-alpha.2.tgz","fileCount":224,"integrity":"sha512-CFUQGAKRuCuFL5Yjb4Bn+hap5lS2q/ee6EujXd3ts2FsDyLMYy4RL3bqlTAYoawfMYuO32EUI0bVD5sMjr8C+g==","signatures":[{"sig":"MEUCIQDm8pFyjT7SHhN+I8m/WFTVux7AMV5/lTt9R3JuCevzfwIgJgaQ7D5CC2dUgSwFF/oC4bgig7ZEHtBv4YZIG4tXC34=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":1692898},"main":"dist/index.js","type":"module","types":"dist/index.d.ts","exports":{".":"./dist/index.js"},"gitHead":"eddd37df1857aa406d944f35a110323012f169a3","scripts":{"test":"vitest run","build":"tsc"},"_npmUser":{"name":"ruvnet","email":"ruv@ruv.net"},"_npmVersion":"10.9.4","description":"Neural module - SONA learning integration, neural modes","directories":{},"_nodeVersion":"22.21.1","dependencies":{"@ruvector/sona":"latest","@claude-flow/memory":"^3.0.0-alpha.2"},"publishConfig":{"tag":"v3alpha","access":"public"},"_hasShrinkwrap":false,"readmeFilename":"README.md","_npmOperationalInternal":{"tmp":"tmp/neural_3.0.0-alpha.2_1767737955353_0.2694762408473992","host":"s3://npm-registry-packages-npm-production"}},"3.0.0-alpha.7":{"name":"@claude-flow/neural","version":"3.0.0-alpha.7","_id":"@claude-flow/neural@3.0.0-alpha.7","maintainers":[{"name":"ruvnet","email":"ruv@ruv.net"}],"dist":{"shasum":"0f1d7afa76451954855aaa80f714e90c1c7a400d","tarball":"https://registry.npmjs.org/@claude-flow/neural/-/neural-3.0.0-alpha.7.tgz","fileCount":232,"integrity":"sha512-OsL/IPMa62S3pwRo0EZ5tAbEdyhD6ALrUZdEj5o6MTPmFt5Xn6PD5uWcX2C5yEMCG/sAIM+Lpb3MDKqIi9avHA==","signatures":[{"sig":"MEYCIQCOFW15LHnFgTgNBsUHfqw8Jyt9tKw7LaQhW3acjadG0QIhANB+0eieVzmpCCVa86rIjxYISU3T2ks16gRWBjtYSICZ","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":1689811},"main":"dist/index.js","type":"module","types":"dist/index.d.ts","exports":{".":"./dist/index.js"},"gitHead":"931dbc25a418d441c8605c0bd66fb19614b97647","scripts":{"test":"vitest run","build":"tsc"},"_npmUser":{"name":"ruvnet","email":"ruv@ruv.net"},"_npmVersion":"10.9.4","description":"Neural module - SONA learning integration, neural modes","directories":{},"_nodeVersion":"22.21.1","dependencies":{"@ruvector/sona":"latest","@claude-flow/memory":"^3.0.0-alpha.2"},"publishConfig":{"tag":"v3alpha","access":"public"},"_hasShrinkwrap":false,"readmeFilename":"README.md","_npmOperationalInternal":{"tmp":"tmp/neural_3.0.0-alpha.7_1769209597349_0.054544506348519706","host":"s3://npm-registry-packages-npm-production"}},"3.0.0-alpha.8":{"name":"@claude-flow/neural","version":"3.0.0-alpha.8","keywords":["ai","agents","ai-agents","multi-agent","multi-agent-systems","agentic","agentic-ai","agentic-systems","claude-flow","ruflo","claude","claude-code","anthropic","neural","neural-network","neural-networks","sona","self-optimizing","self-improving","adaptive-learning","continual-learning","lifelong-learning","online-learning","reinforcement-learning","rl","deep-rl","ppo","proximal-policy-optimization","dqn","deep-q-network","a2c","advantage-actor-critic","q-learning","sarsa","decision-transformer","curiosity-driven","exploration","policy-gradient","value-function","lora","low-rank-adaptation","ewc","elastic-weight-consolidation","catastrophic-forgetting","flash-attention","fast-attention","mixture-of-experts","moe","expert-routing","trajectory","trajectory-learning","experience-replay","pattern-recognition","pattern-matching","pattern-extraction","pattern-evolution","reasoning","reasoning-bank","reasoning-traces","self-consistency","ensemble","embeddings","vector-embeddings","vector-search","hnsw","semantic-search","cosine-similarity","agentdb","memory","knowledge-distillation","model-compression","quantization","fine-tuning","transfer-learning","meta-learning","mcp","model-context-protocol","llm","llm-agents","agent-orchestration","agent-coordination","ml","machine-learning","typescript","esm","wasm","open-source"],"author":{"url":"https://github.com/ruvnet","name":"ruvnet"},"license":"MIT","_id":"@claude-flow/neural@3.0.0-alpha.8","maintainers":[{"name":"ruvnet","email":"ruv@ruv.net"}],"homepage":"https://github.com/ruvnet/ruflo","bugs":{"url":"https://github.com/ruvnet/ruflo/issues"},"dist":{"shasum":"cedb4a69e1821f7fa68fb6560dd01c8660018fdc","tarball":"https://registry.npmjs.org/@claude-flow/neural/-/neural-3.0.0-alpha.8.tgz","fileCount":130,"integrity":"sha512-+aPg0o6NfaGgw+toEVYdnxxbdtJTOBCtZcqC3BMHkor2AW3UigXoldhMc9T1w+Top11biZy3ZwrvwXHHcLjD4g==","signatures":[{"sig":"MEYCIQDpcwg05ot60yPE20wsJVIBWMoiZTWPrbwcIqtYbJZXsAIhAO2HcslAI8f9AcvPcz5OyCkWZrI6ToEm91NbJl/ZC3LM","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":828557},"main":"dist/index.js","type":"module","types":"dist/index.d.ts","exports":{".":"./dist/index.js"},"gitHead":"6b9392f089b57b4082818820f1972c6dfa07110f","scripts":{"test":"vitest run","build":"tsc"},"_npmUser":{"name":"ruvnet","email":"ruv@ruv.net"},"repository":{"url":"git+https://github.com/ruvnet/ruflo.git","type":"git","directory":"v3/@claude-flow/neural"},"_npmVersion":"10.9.4","description":"Self-Optimizing Neural Architecture (SONA) for Claude Flow — adaptive learning, trajectory tracking, pattern reuse, 7 RL algorithms (PPO/A2C/DQN/Q-Learning/SARSA/Decision Transformer/Curiosity), Flash Attention, MoE routing, LoRA, EWC++ for continual lear","directories":{},"_nodeVersion":"22.22.1","dependencies":{"@ruvector/sona":"latest","@claude-flow/memory":"^3.0.0-alpha.2"},"publishConfig":{"tag":"v3alpha","access":"public"},"_hasShrinkwrap":false,"readmeFilename":"README.md","optionalDependencies":{"agentdb":"^2.0.0 || ^3.0.0-alpha.1"},"_npmOperationalInternal":{"tmp":"tmp/neural_3.0.0-alpha.8_1778035953705_0.7151014112558725","host":"s3://npm-registry-packages-npm-production"}},"3.0.0-alpha.9":{"name":"@claude-flow/neural","version":"3.0.0-alpha.9","keywords":["ai","agents","ai-agents","multi-agent","multi-agent-systems","agentic","agentic-ai","agentic-systems","claude-flow","ruflo","claude","claude-code","anthropic","neural","neural-network","neural-networks","sona","self-optimizing","self-improving","adaptive-learning","continual-learning","lifelong-learning","online-learning","reinforcement-learning","rl","deep-rl","ppo","proximal-policy-optimization","dqn","deep-q-network","a2c","advantage-actor-critic","q-learning","sarsa","decision-transformer","curiosity-driven","exploration","policy-gradient","value-function","lora","low-rank-adaptation","ewc","elastic-weight-consolidation","catastrophic-forgetting","flash-attention","fast-attention","mixture-of-experts","moe","expert-routing","trajectory","trajectory-learning","experience-replay","pattern-recognition","pattern-matching","pattern-extraction","pattern-evolution","reasoning","reasoning-bank","reasoning-traces","self-consistency","ensemble","embeddings","vector-embeddings","vector-search","hnsw","semantic-search","cosine-similarity","agentdb","memory","knowledge-distillation","model-compression","quantization","fine-tuning","transfer-learning","meta-learning","mcp","model-context-protocol","llm","llm-agents","agent-orchestration","agent-coordination","ml","machine-learning","typescript","esm","wasm","open-source"],"author":{"url":"https://github.com/ruvnet","name":"ruvnet"},"license":"MIT","_id":"@claude-flow/neural@3.0.0-alpha.9","maintainers":[{"name":"ruvnet","email":"ruv@ruv.net"}],"homepage":"https://github.com/ruvnet/ruflo","bugs":{"url":"https://github.com/ruvnet/ruflo/issues"},"dist":{"shasum":"fca3943d58db13f2b9da2fea5a49d983da1ddfc4","tarball":"https://registry.npmjs.org/@claude-flow/neural/-/neural-3.0.0-alpha.9.tgz","fileCount":130,"integrity":"sha512-u7mx6rQxHrpCyKVtP600QorSJrEhoqYEyGZgYVU1kGWwYitScJH3rzWzss95Dn+RazcCAk7yElEG/iSbhtxU6g==","signatures":[{"sig":"MEUCIEPfswsUA5rWnabJS2IP0WVHFo6CpH62dTr6vpMf85rAAiEAgRM2LF9Mi8Tvsn0UZMiuXXeqmi02EaabbctQtKpNjMs=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":829432},"main":"dist/index.js","type":"module","types":"dist/index.d.ts","exports":{".":"./dist/index.js"},"gitHead":"ca0a6fa5cb1678b5c57c9289bc09a036f7308c61","scripts":{"test":"vitest run","build":"tsc"},"_npmUser":{"name":"ruvnet","email":"ruv@ruv.net"},"repository":{"url":"git+https://github.com/ruvnet/ruflo.git","type":"git","directory":"v3/@claude-flow/neural"},"_npmVersion":"10.9.4","description":"Self-Optimizing Neural Architecture (SONA) for Claude Flow — adaptive learning, trajectory tracking, pattern reuse, 7 RL algorithms (PPO/A2C/DQN/Q-Learning/SARSA/Decision Transformer/Curiosity), Flash Attention, MoE routing, LoRA, EWC++ for continual lear","directories":{},"_nodeVersion":"22.22.1","dependencies":{"@ruvector/sona":"0.1.5","@claude-flow/memory":"^3.0.0-alpha.16"},"publishConfig":{"tag":"v3alpha","access":"public"},"_hasShrinkwrap":false,"optionalDependencies":{"agentdb":"^2.0.0 || ^3.0.0-alpha.1"},"_npmOperationalInternal":{"tmp":"tmp/neural_3.0.0-alpha.9_1778963571481_0.4326580994822209","host":"s3://npm-registry-packages-npm-production"}},"3.0.0-alpha.10":{"name":"@claude-flow/neural","version":"3.0.0-alpha.10","keywords":["ai","agents","ai-agents","multi-agent","multi-agent-systems","agentic","agentic-ai","agentic-systems","claude-flow","ruflo","claude","claude-code","anthropic","neural","neural-network","neural-networks","sona","self-optimizing","self-improving","adaptive-learning","continual-learning","lifelong-learning","online-learning","reinforcement-learning","rl","deep-rl","ppo","proximal-policy-optimization","dqn","deep-q-network","a2c","advantage-actor-critic","q-learning","sarsa","decision-transformer","curiosity-driven","exploration","policy-gradient","value-function","lora","low-rank-adaptation","ewc","elastic-weight-consolidation","catastrophic-forgetting","flash-attention","fast-attention","mixture-of-experts","moe","expert-routing","trajectory","trajectory-learning","experience-replay","pattern-recognition","pattern-matching","pattern-extraction","pattern-evolution","reasoning","reasoning-bank","reasoning-traces","self-consistency","ensemble","embeddings","vector-embeddings","vector-search","hnsw","semantic-search","cosine-similarity","agentdb","memory","knowledge-distillation","model-compression","quantization","fine-tuning","transfer-learning","meta-learning","mcp","model-context-protocol","llm","llm-agents","agent-orchestration","agent-coordination","ml","machine-learning","typescript","esm","wasm","open-source"],"author":{"url":"https://github.com/ruvnet","name":"ruvnet"},"license":"MIT","_id":"@claude-flow/neural@3.0.0-alpha.10","maintainers":[{"name":"ruvnet","email":"ruv@ruv.net"}],"homepage":"https://github.com/ruvnet/ruflo","bugs":{"url":"https://github.com/ruvnet/ruflo/issues"},"dist":{"shasum":"fd3486f81d71af922f10e2ecc7a70de1012f6ac1","tarball":"https://registry.npmjs.org/@claude-flow/neural/-/neural-3.0.0-alpha.10.tgz","fileCount":130,"integrity":"sha512-5Qj3cC+MuZvXBbuiEBKCehwdBUaP9YSSAQ9IA04bf4iPSvPJOwIpQk2xsJPRa8IwySFTP2bkvQePswpBij8xzg==","signatures":[{"sig":"MEYCIQDi8bNz5JpnFwYmbax/WzVT/4NteNxiWPAeh5lLVe6uhQIhAN4UO59N5IyzNY9F49lGNWwd5B6Pk6Zt4zkjFjIUXofr","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"},{"sig":"MEQCIF4JmJ4FQjAyGxm+kYjv++CUsG8XImF+FZkvpWmBxy1bAiBKL8l2FX0Bl/YyNYQtVaN+x0/M85kOzNhYDn2jjxAhIw==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":834471},"main":"dist/index.js","type":"module","_from":"file:/home/ruvultra/.cache/claude-code/tmp/claude-1000/-home-ruvultra-projects-ruflo/7343707a-7e8f-42c1-bc6a-c657714d8da3/scratchpad/packs/claude-flow-neural-3.0.0-alpha.10.tgz","types":"dist/index.d.ts","exports":{".":"./dist/index.js"},"scripts":{"test":"vitest run","build":"tsc"},"_npmUser":{"name":"ruvnet","email":"ruv@ruv.net"},"_resolved":"/home/ruvultra/.cache/claude-code/tmp/claude-1000/-home-ruvultra-projects-ruflo/7343707a-7e8f-42c1-bc6a-c657714d8da3/scratchpad/packs/claude-flow-neural-3.0.0-alpha.10.tgz","_integrity":"sha512-5Qj3cC+MuZvXBbuiEBKCehwdBUaP9YSSAQ9IA04bf4iPSvPJOwIpQk2xsJPRa8IwySFTP2bkvQePswpBij8xzg==","repository":{"url":"git+https://github.com/ruvnet/ruflo.git","type":"git","directory":"v3/@claude-flow/neural"},"_npmVersion":"10.9.8","description":"Self-Optimizing Neural Architecture (SONA) for Claude Flow — adaptive learning, trajectory tracking, pattern reuse, 7 RL algorithms (PPO/A2C/DQN/Q-Learning/SARSA/Decision Transformer/Curiosity), Flash Attention, MoE routing, LoRA, EWC++ for continual lear","directories":{},"_nodeVersion":"22.23.2","dependencies":{"@ruvector/sona":"0.1.5","@claude-flow/memory":"^3.0.0-alpha.16"},"publishConfig":{"tag":"v3alpha","access":"public"},"_hasShrinkwrap":false,"readmeFilename":"README.md","optionalDependencies":{"agentdb":"^2.0.0 || ^3.0.0-alpha.1"},"_npmOperationalInternal":{"tmp":"tmp/neural_3.0.0-alpha.10_1790437221222_0.05313325927066237","host":"s3://npm-registry-packages-npm-production"}},"3.0.0":{"name":"@claude-flow/neural","version":"3.0.0","keywords":["ai","agents","ai-agents","multi-agent","multi-agent-systems","agentic","agentic-ai","agentic-systems","claude-flow","ruflo","claude","claude-code","anthropic","neural","neural-network","neural-networks","sona","self-optimizing","self-improving","adaptive-learning","continual-learning","lifelong-learning","online-learning","reinforcement-learning","rl","deep-rl","ppo","proximal-policy-optimization","dqn","deep-q-network","a2c","advantage-actor-critic","q-learning","sarsa","decision-transformer","curiosity-driven","exploration","policy-gradient","value-function","lora","low-rank-adaptation","ewc","elastic-weight-consolidation","catastrophic-forgetting","flash-attention","fast-attention","mixture-of-experts","moe","expert-routing","trajectory","trajectory-learning","experience-replay","pattern-recognition","pattern-matching","pattern-extraction","pattern-evolution","reasoning","reasoning-bank","reasoning-traces","self-consistency","ensemble","embeddings","vector-embeddings","vector-search","hnsw","semantic-search","cosine-similarity","agentdb","memory","knowledge-distillation","model-compression","quantization","fine-tuning","transfer-learning","meta-learning","mcp","model-context-protocol","llm","llm-agents","agent-orchestration","agent-coordination","ml","machine-learning","typescript","esm","wasm","open-source"],"author":{"url":"https://github.com/ruvnet","name":"ruvnet"},"license":"MIT","_id":"@claude-flow/neural@3.0.0","maintainers":[{"name":"ruvnet","email":"ruv@ruv.net"}],"homepage":"https://github.com/ruvnet/ruflo","bugs":{"url":"https://github.com/ruvnet/ruflo/issues"},"dist":{"shasum":"88f704422b8959615bb3879f5427d2face4e1206","tarball":"https://registry.npmjs.org/@claude-flow/neural/-/neural-3.0.0.tgz","fileCount":130,"integrity":"sha512-AEsuXXZSGqNVFQaVSn2XHBnDifkmJlcDm6xO3UyDo7vK0YpVJh0meCxO7T+EYDmuwmOlu0/M4e9VSgIlhT7ePQ==","signatures":[{"sig":"MEUCIENBi93jSXcEnPDZCFi3ddrsNxXWM1A7MSCCzCRK302EAiEA5y4726bhBbR976FhU4uLH1hQnQDTyKh0oOnWwtOf+34=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"},{"sig":"MEYCIQCOgHG3fBKMoyw3SJYDZQxz6NJmbxad/H2ZMJT86XmdGgIhAI4crEaEohfmDtrltmAiAPaL0Tc2a8sEz7FwvmhCDjDT","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":834431},"main":"dist/index.js","type":"module","types":"dist/index.d.ts","exports":{".":"./dist/index.js"},"gitHead":"7307d1d86a6e932b0027b070eed0796e231aecee","scripts":{"test":"vitest run","build":"tsc"},"_npmUser":{"name":"ruvnet","email":"ruv@ruv.net"},"repository":{"url":"git+https://github.com/ruvnet/ruflo.git","type":"git","directory":"v3/@claude-flow/neural"},"_npmVersion":"10.9.8","description":"Self-Optimizing Neural Architecture (SONA) for Claude Flow — adaptive learning, trajectory tracking, pattern reuse, 7 RL algorithms (PPO/A2C/DQN/Q-Learning/SARSA/Decision Transformer/Curiosity), Flash Attention, MoE routing, LoRA, EWC++ for continual lear","directories":{},"_nodeVersion":"22.23.2","dependencies":{"@ruvector/sona":"0.1.5","@claude-flow/memory":"^3.0.0"},"publishConfig":{"access":"public"},"_hasShrinkwrap":false,"optionalDependencies":{"agentdb":"^2.0.0 || ^3.0.0-alpha.1"},"_npmOperationalInternal":{"tmp":"tmp/neural_3.0.0_1790629105119_0.6222912339546691","host":"s3://npm-registry-packages-npm-production"}},"3.0.1":{"name":"@claude-flow/neural","version":"3.0.1","keywords":["ai","agents","ai-agents","multi-agent","multi-agent-systems","agentic","agentic-ai","agentic-systems","claude-flow","ruflo","claude","claude-code","anthropic","neural","neural-network","neural-networks","sona","self-optimizing","self-improving","adaptive-learning","continual-learning","lifelong-learning","online-learning","reinforcement-learning","rl","deep-rl","ppo","proximal-policy-optimization","dqn","deep-q-network","a2c","advantage-actor-critic","q-learning","sarsa","decision-transformer","curiosity-driven","exploration","policy-gradient","value-function","lora","low-rank-adaptation","ewc","elastic-weight-consolidation","catastrophic-forgetting","flash-attention","fast-attention","mixture-of-experts","moe","expert-routing","trajectory","trajectory-learning","experience-replay","pattern-recognition","pattern-matching","pattern-extraction","pattern-evolution","reasoning","reasoning-bank","reasoning-traces","self-consistency","ensemble","embeddings","vector-embeddings","vector-search","hnsw","semantic-search","cosine-similarity","agentdb","memory","knowledge-distillation","model-compression","quantization","fine-tuning","transfer-learning","meta-learning","mcp","model-context-protocol","llm","llm-agents","agent-orchestration","agent-coordination","ml","machine-learning","typescript","esm","wasm","open-source"],"author":{"url":"https://github.com/ruvnet","name":"ruvnet"},"license":"MIT","_id":"@claude-flow/neural@3.0.1","maintainers":[{"name":"ruvnet","email":"ruv@ruv.net"}],"homepage":"https://github.com/ruvnet/ruflo","bugs":{"url":"https://github.com/ruvnet/ruflo/issues"},"dist":{"shasum":"f129a1378c63ca9a5bd40732d9643499c29176d4","tarball":"https://registry.npmjs.org/@claude-flow/neural/-/neural-3.0.1.tgz","fileCount":130,"integrity":"sha512-bAxXBZrLasgxmkpkmavkv8GGSx3LgZeKJQGZei7S7aoIZHzh/z6HJPerjpUn7oZiCH1NAQjUDnCg/rNU3/GjbQ==","signatures":[{"sig":"MEQCIG5a5LCl0IOAAJDJbmUkheh7ZFH2oNZ6N3lyNKhxCjmwAiAvnKFGp8JVKtmgRQa1XNVF+LJ3bnhF1mtk02/OANyi+Q==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"},{"sig":"MEUCIQDuxO6g1WJKr0QjCz1nZmPIV/fmQ4fYgLjxJIWillOdsAIgdTw+IkAweZTBerEjlATAZq5S6iZDXzAQ/W6ToWhnvbo=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":844890},"main":"dist/index.js","type":"module","types":"dist/index.d.ts","exports":{".":"./dist/index.js"},"scripts":{"test":"vitest run","build":"tsc"},"_npmUser":{"name":"ruvnet","email":"ruv@ruv.net"},"repository":{"url":"git+https://github.com/ruvnet/ruflo.git","type":"git","directory":"v3/@claude-flow/neural"},"_npmVersion":"10.9.8","description":"Self-Optimizing Neural Architecture (SONA) for Claude Flow — adaptive learning, trajectory tracking, pattern reuse, 7 RL algorithms (PPO/A2C/DQN/Q-Learning/SARSA/Decision Transformer/Curiosity), Flash Attention, MoE routing, LoRA, EWC++ for continual lear","directories":{},"_nodeVersion":"22.23.2","dependencies":{"@ruvector/sona":"0.1.5","@claude-flow/memory":"^3.0.0"},"publishConfig":{"access":"public"},"_hasShrinkwrap":false,"optionalDependencies":{"agentdb":"^2.0.0 || ^3.0.0-alpha.1"},"_npmOperationalInternal":{"tmp":"tmp/neural_3.0.1_1793122976897_0.7239576908716338","host":"s3://npm-registry-packages-npm-production"}},"3.0.2":{"name":"@claude-flow/neural","version":"3.0.2","keywords":["ai","agents","ai-agents","multi-agent","multi-agent-systems","agentic","agentic-ai","agentic-systems","claude-flow","ruflo","claude","claude-code","anthropic","neural","neural-network","neural-networks","sona","self-optimizing","self-improving","adaptive-learning","continual-learning","lifelong-learning","online-learning","reinforcement-learning","rl","deep-rl","ppo","proximal-policy-optimization","dqn","deep-q-network","a2c","advantage-actor-critic","q-learning","sarsa","decision-transformer","curiosity-driven","exploration","policy-gradient","value-function","lora","low-rank-adaptation","ewc","elastic-weight-consolidation","catastrophic-forgetting","flash-attention","fast-attention","mixture-of-experts","moe","expert-routing","trajectory","trajectory-learning","experience-replay","pattern-recognition","pattern-matching","pattern-extraction","pattern-evolution","reasoning","reasoning-bank","reasoning-traces","self-consistency","ensemble","embeddings","vector-embeddings","vector-search","hnsw","semantic-search","cosine-similarity","agentdb","memory","knowledge-distillation","model-compression","quantization","fine-tuning","transfer-learning","meta-learning","mcp","model-context-protocol","llm","llm-agents","agent-orchestration","agent-coordination","ml","machine-learning","typescript","esm","wasm","open-source"],"author":{"url":"https://github.com/ruvnet","name":"ruvnet"},"license":"MIT","_id":"@claude-flow/neural@3.0.2","maintainers":[{"name":"ruvnet","email":"ruv@ruv.net"}],"homepage":"https://github.com/ruvnet/ruflo","bugs":{"url":"https://github.com/ruvnet/ruflo/issues"},"dist":{"shasum":"da161bfa6a6a846fcfae12cbbcfe2b19b298dc7f","tarball":"https://registry.npmjs.org/@claude-flow/neural/-/neural-3.0.2.tgz","fileCount":130,"integrity":"sha512-U71klxzU5pk48GLiT1x2XYNR0vgZPJeDlyVun6qR87UOb5nFs8o+w+al3/9qeSZ97zVbicoIkeMCU48DewBBqA==","signatures":[{"sig":"MEYCIQChY5Z+kZvjmvehe7r/VV5do1VfTGwi1/gdUI+prYvJ0wIhAOBelK4Sq8ScRjAIic9CdilJPN1G0lXkm6OeY6jvTlw7","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"},{"sig":"MEYCIQCQKWVqGKuwm0eHr1B/aKRYbZ0FSBb4AcrXeLZ+5vTP8AIhALgUmPggH5syliY8G9t7RQkYiisWdCS73UHWHjyj3muG","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":847069},"main":"dist/index.js","type":"module","types":"dist/index.d.ts","exports":{".":"./dist/index.js"},"scripts":{"test":"vitest run","build":"tsc"},"_npmUser":{"name":"ruvnet","email":"ruv@ruv.net"},"repository":{"url":"git+https://github.com/ruvnet/ruflo.git","type":"git","directory":"v3/@claude-flow/neural"},"_npmVersion":"10.9.8","description":"Self-Optimizing Neural Architecture (SONA) for Claude Flow — adaptive learning, trajectory tracking, pattern reuse, 7 RL algorithms (PPO/A2C/DQN/Q-Learning/SARSA/Decision Transformer/Curiosity), Flash Attention, MoE routing, LoRA, EWC++ for continual lear","directories":{},"_nodeVersion":"22.23.2","dependencies":{"@ruvector/sona":"0.1.5","@claude-flow/memory":"^3.0.0"},"publishConfig":{"access":"public"},"_hasShrinkwrap":false,"optionalDependencies":{"agentdb":"^2.0.0 || ^3.0.0-alpha.1"},"_npmOperationalInternal":{"tmp":"tmp/neural_3.0.2_1793550928166_0.3195066606694159","host":"s3://npm-registry-packages-npm-production"}},"3.0.3":{"name":"@claude-flow/neural","version":"3.0.3","keywords":["ai","agents","ai-agents","multi-agent","multi-agent-systems","agentic","agentic-ai","agentic-systems","claude-flow","ruflo","claude","claude-code","anthropic","neural","neural-network","neural-networks","sona","self-optimizing","self-improving","adaptive-learning","continual-learning","lifelong-learning","online-learning","reinforcement-learning","rl","deep-rl","ppo","proximal-policy-optimization","dqn","deep-q-network","a2c","advantage-actor-critic","q-learning","sarsa","decision-transformer","curiosity-driven","exploration","policy-gradient","value-function","lora","low-rank-adaptation","ewc","elastic-weight-consolidation","catastrophic-forgetting","flash-attention","fast-attention","mixture-of-experts","moe","expert-routing","trajectory","trajectory-learning","experience-replay","pattern-recognition","pattern-matching","pattern-extraction","pattern-evolution","reasoning","reasoning-bank","reasoning-traces","self-consistency","ensemble","embeddings","vector-embeddings","vector-search","hnsw","semantic-search","cosine-similarity","agentdb","memory","knowledge-distillation","model-compression","quantization","fine-tuning","transfer-learning","meta-learning","mcp","model-context-protocol","llm","llm-agents","agent-orchestration","agent-coordination","ml","machine-learning","typescript","esm","wasm","open-source"],"author":{"url":"https://github.com/ruvnet","name":"ruvnet"},"license":"MIT","_id":"@claude-flow/neural@3.0.3","maintainers":[{"name":"ruvnet","email":"ruv@ruv.net"}],"homepage":"https://github.com/ruvnet/ruflo","bugs":{"url":"https://github.com/ruvnet/ruflo/issues"},"dist":{"shasum":"abe05f278d0613c4b79ffef70858a0c8a9675345","tarball":"https://registry.npmjs.org/@claude-flow/neural/-/neural-3.0.3.tgz","fileCount":130,"integrity":"sha512-u9E4i1givJUo25Y/2hZLjzqI0IJv+Tov2H2vLDYrSFga/YLifQ6sM596+3vZeHksYMciSJ6U7Pqn5JBl5vbkiA==","signatures":[{"sig":"MEUCIE7Ww1KfSqNSymQ6VdfNUUO2KnHaN3oDQ4sbL2M1CNCyAiEA+FJ+G0n//9/WHnv64R8kh6b9jRtZhT4BrTMwaVEKP9k=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"},{"sig":"MEQCID9/TH6FeUOgWol1oZi8CPMuRwJT2nPO/4gEkmwamYR+AiA7yGrnmJQ4+k4BpQ8l4X4nue7Q4gaAA+K8j4GlECpTGw==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":847070},"main":"dist/index.js","type":"module","types":"dist/index.d.ts","exports":{".":"./dist/index.js"},"scripts":{"test":"vitest run","build":"tsc"},"_npmUser":{"name":"ruvnet","email":"ruv@ruv.net"},"repository":{"url":"git+https://github.com/ruvnet/ruflo.git","type":"git","directory":"v3/@claude-flow/neural"},"_npmVersion":"10.9.8","description":"Self-Optimizing Neural Architecture (SONA) for Claude Flow — adaptive learning, trajectory tracking, pattern reuse, 7 RL algorithms (PPO/A2C/DQN/Q-Learning/SARSA/Decision Transformer/Curiosity), Flash Attention, MoE routing, LoRA, EWC++ for continual lear","directories":{},"_nodeVersion":"22.23.2","dependencies":{"@ruvector/sona":"0.1.11","@claude-flow/memory":"^3.0.0"},"publishConfig":{"access":"public"},"_hasShrinkwrap":false,"optionalDependencies":{"agentdb":"^2.0.0 || ^3.0.0-alpha.1"},"_npmOperationalInternal":{"tmp":"tmp/neural_3.0.3_1793969194622_0.2679195615438533","host":"s3://npm-registry-packages-npm-production"}},"3.1.0":{"name":"@claude-flow/neural","version":"3.1.0","keywords":["ai","agents","ai-agents","multi-agent","multi-agent-systems","agentic","agentic-ai","agentic-systems","claude-flow","ruflo","claude","claude-code","anthropic","neural","neural-network","neural-networks","sona","self-optimizing","self-improving","adaptive-learning","continual-learning","lifelong-learning","online-learning","reinforcement-learning","rl","deep-rl","ppo","proximal-policy-optimization","dqn","deep-q-network","a2c","advantage-actor-critic","q-learning","sarsa","decision-transformer","curiosity-driven","exploration","policy-gradient","value-function","lora","low-rank-adaptation","ewc","elastic-weight-consolidation","catastrophic-forgetting","flash-attention","fast-attention","mixture-of-experts","moe","expert-routing","trajectory","trajectory-learning","experience-replay","pattern-recognition","pattern-matching","pattern-extraction","pattern-evolution","reasoning","reasoning-bank","reasoning-traces","self-consistency","ensemble","embeddings","vector-embeddings","vector-search","hnsw","semantic-search","cosine-similarity","agentdb","memory","knowledge-distillation","model-compression","quantization","fine-tuning","transfer-learning","meta-learning","mcp","model-context-protocol","llm","llm-agents","agent-orchestration","agent-coordination","ml","machine-learning","typescript","esm","wasm","open-source"],"author":{"url":"https://github.com/ruvnet","name":"ruvnet"},"license":"MIT","_id":"@claude-flow/neural@3.1.0","maintainers":[{"name":"ruvnet","email":"ruv@ruv.net"}],"homepage":"https://github.com/ruvnet/ruflo","bugs":{"url":"https://github.com/ruvnet/ruflo/issues"},"dist":{"shasum":"7ec69ecd25f95ab20c4401c52ccef6f404fd842f","tarball":"https://registry.npmjs.org/@claude-flow/neural/-/neural-3.1.0.tgz","fileCount":134,"integrity":"sha512-5Wpl4jP0sV3dlV7M8C5Y/YDIR6s+JVauxutKc8fqEnUCeg5x1TIi9thsUsyZ7BgaTdZEyYiRAzqnwS00O5IVUg==","signatures":[{"sig":"MEQCIAL9T9rBv1UC+JS2cb08LHEygLe9P/MZs5QA/UvcK8j9AiAbJbDsihr+P3QyUNPIaoj3dKpPQOz/IdL8vflICHwevQ==","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"},{"sig":"MEYCIQD0Q/Q/7BVzpNdek6cBg6fysA4XllyymNIklAUZWWh3pQIhAMMhoipJDR62sAaBGyqEHsHTP7tEnXuET4xAi3ZRCaj6","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":864130},"main":"dist/index.js","type":"module","types":"dist/index.d.ts","exports":{".":"./dist/index.js"},"scripts":{"test":"vitest run","build":"tsc"},"_npmUser":{"name":"ruvnet","email":"ruv@ruv.net"},"repository":{"url":"git+https://github.com/ruvnet/ruflo.git","type":"git","directory":"v3/@claude-flow/neural"},"_npmVersion":"10.9.8","description":"Self-Optimizing Neural Architecture (SONA) for Claude Flow — adaptive learning, trajectory tracking, pattern reuse, 7 RL algorithms (PPO/A2C/DQN/Q-Learning/SARSA/Decision Transformer/Curiosity), Flash Attention, MoE routing, LoRA, EWC++ for continual lear","directories":{},"_nodeVersion":"22.23.2","dependencies":{"@ruvector/sona":"0.1.11","@claude-flow/memory":"^3.0.0"},"publishConfig":{"access":"public"},"_hasShrinkwrap":false,"optionalDependencies":{"agentdb":"^2.0.0 || ^3.0.0-alpha.1"},"_npmOperationalInternal":{"tmp":"tmp/neural_3.1.0_1795067503884_0.21693907181420946","host":"s3://npm-registry-packages-npm-production"}},"3.1.1":{"_id":"@claude-flow/neural@3.1.1","bugs":{"url":"https://github.com/ruvnet/ruflo/issues"},"dist":{"shasum":"53e161c3b6ed783f3f04986d00b09be232ca26aa","tarball":"https://registry.npmjs.org/@claude-flow/neural/-/neural-3.1.1.tgz","fileCount":134,"integrity":"sha512-cHd1Wv5j9oRyz0cjNZn9tpGuH7d7sZsRRzOLRWJ+izl4v8u/y+GQd/Xyk3DtaCu3JCLSG3So84Vi5ZB7fj6t2g==","signatures":[{"sig":"MEUCIQCxbVa263GwW+yhH3DZWVl67oh3tbboOdSvkJAHi1ch2QIgZx+2yU488RwfJzj5n4jzrOno480nzghI4POShwPq34M=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"},{"keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U","sig":"MEYCIQCkhVLnwR2q/HoppOU9ZuJ9dJRXvBRXjJWF7P68ZUGjywIhAJ9SQrZpbN4Ri/kUEx4fgiJW0TY2Y4QV0eyLRLuYdN+Z"}],"unpackedSize":863872},"main":"dist/index.js","name":"@claude-flow/neural","type":"module","types":"dist/index.d.ts","author":{"url":"https://github.com/ruvnet","name":"ruvnet"},"exports":{".":"./dist/index.js"},"license":"MIT","scripts":{"test":"vitest run","build":"tsc"},"version":"3.1.1","_npmUser":{"name":"ruvnet","email":"ruv@ruv.net"},"homepage":"https://github.com/ruvnet/ruflo","keywords":["ai","agents","ai-agents","multi-agent","multi-agent-systems","agentic","agentic-ai","agentic-systems","claude-flow","ruflo","claude","claude-code","anthropic","neural","neural-network","neural-networks","sona","self-optimizing","self-improving","adaptive-learning","continual-learning","lifelong-learning","online-learning","reinforcement-learning","rl","deep-rl","ppo","proximal-policy-optimization","dqn","deep-q-network","a2c","advantage-actor-critic","q-learning","sarsa","decision-transformer","curiosity-driven","exploration","policy-gradient","value-function","lora","low-rank-adaptation","ewc","elastic-weight-consolidation","catastrophic-forgetting","flash-attention","fast-attention","mixture-of-experts","moe","expert-routing","trajectory","trajectory-learning","experience-replay","pattern-recognition","pattern-matching","pattern-extraction","pattern-evolution","reasoning","reasoning-bank","reasoning-traces","self-consistency","ensemble","embeddings","vector-embeddings","vector-search","hnsw","semantic-search","cosine-similarity","agentdb","memory","knowledge-distillation","model-compression","quantization","fine-tuning","transfer-learning","meta-learning","mcp","model-context-protocol","llm","llm-agents","agent-orchestration","agent-coordination","ml","machine-learning","typescript","esm","wasm","open-source"],"repository":{"url":"git+https://github.com/ruvnet/ruflo.git","type":"git","directory":"v3/@claude-flow/neural"},"_npmVersion":"10.9.8","description":"Self-Optimizing Neural Architecture (SONA) for Claude Flow — adaptive learning, trajectory tracking, pattern reuse, 7 RL algorithms (PPO/A2C/DQN/Q-Learning/SARSA/Decision Transformer/Curiosity), Flash Attention, MoE routing, LoRA, EWC++ for continual lear","directories":{},"maintainers":[{"name":"ruvnet","email":"ruv@ruv.net"}],"_nodeVersion":"22.23.2","dependencies":{"@ruvector/sona":"0.1.11","@claude-flow/memory":"^3.0.0"},"publishConfig":{"access":"public"},"_hasShrinkwrap":false,"optionalDependencies":{"agentdb":"^2.0.0 || ^3.0.0-alpha.1"},"_npmOperationalInternal":{"host":"s3://npm-registry-packages-npm-production","tmp":"tmp/neural_3.1.1_1795100583437_0.8834117400708721"}}},"time":{"created":"2026-01-06T21:44:48.870Z","modified":"2026-11-19T15:03:03.944Z","3.0.0-alpha.1":"2026-01-06T21:44:49.113Z","3.0.0-alpha.2":"2026-01-06T22:19:15.533Z","3.0.0-alpha.7":"2026-01-23T23:06:37.553Z","3.0.0-alpha.8":"2026-05-06T02:52:33.992Z","3.0.0-alpha.9":"2026-05-16T20:32:51.692Z","3.0.0-alpha.10":"2026-09-26T15:40:21.309Z","3.0.0":"2026-09-28T20:58:25.231Z","3.0.1":"2026-10-27T17:42:57.019Z","3.0.2":"2026-11-01T16:35:28.240Z","3.0.3":"2026-11-06T12:46:34.730Z","3.1.0":"2026-11-19T05:51:43.988Z","3.1.1":"2026-11-19T15:03:03.570Z"},"bugs":{"url":"https://github.com/ruvnet/ruflo/issues"},"author":{"url":"https://github.com/ruvnet","name":"ruvnet"},"license":"MIT","homepage":"https://github.com/ruvnet/ruflo","keywords":["ai","agents","ai-agents","multi-agent","multi-agent-systems","agentic","agentic-ai","agentic-systems","claude-flow","ruflo","claude","claude-code","anthropic","neural","neural-network","neural-networks","sona","self-optimizing","self-improving","adaptive-learning","continual-learning","lifelong-learning","online-learning","reinforcement-learning","rl","deep-rl","ppo","proximal-policy-optimization","dqn","deep-q-network","a2c","advantage-actor-critic","q-learning","sarsa","decision-transformer","curiosity-driven","exploration","policy-gradient","value-function","lora","low-rank-adaptation","ewc","elastic-weight-consolidation","catastrophic-forgetting","flash-attention","fast-attention","mixture-of-experts","moe","expert-routing","trajectory","trajectory-learning","experience-replay","pattern-recognition","pattern-matching","pattern-extraction","pattern-evolution","reasoning","reasoning-bank","reasoning-traces","self-consistency","ensemble","embeddings","vector-embeddings","vector-search","hnsw","semantic-search","cosine-similarity","agentdb","memory","knowledge-distillation","model-compression","quantization","fine-tuning","transfer-learning","meta-learning","mcp","model-context-protocol","llm","llm-agents","agent-orchestration","agent-coordination","ml","machine-learning","typescript","esm","wasm","open-source"],"repository":{"url":"git+https://github.com/ruvnet/ruflo.git","type":"git","directory":"v3/@claude-flow/neural"},"description":"Self-Optimizing Neural Architecture (SONA) for Claude Flow — adaptive learning, trajectory tracking, pattern reuse, 7 RL algorithms (PPO/A2C/DQN/Q-Learning/SARSA/Decision Transformer/Curiosity), Flash Attention, MoE routing, LoRA, EWC++ for continual lear","maintainers":[{"name":"ruvnet","email":"ruv@ruv.net"}],"readme":"# @claude-flow/neural\n\n[![npm version](https://img.shields.io/npm/v/@claude-flow/neural.svg)](https://www.npmjs.com/package/@claude-flow/neural)\n[![npm downloads](https://img.shields.io/npm/dm/@claude-flow/neural.svg)](https://www.npmjs.com/package/@claude-flow/neural)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)\n[![TypeScript](https://img.shields.io/badge/TypeScript-5.0+-blue.svg)](https://www.typescriptlang.org/)\n\n> Self-Optimizing Neural Architecture (SONA) for Claude Flow V3 — adaptive learning, trajectory tracking, pattern reuse, and 7 RL algorithms in a single package.\n\n## What this is\n\nA self-contained learning module that records agent execution trajectories, distills them into reusable patterns, retrieves matches for new tasks, and adapts via SONA + LoRA + EWC++. Designed to be the substrate that the Claude Flow CLI's intelligence layer composes onto — the package owns the algorithms, the CLI owns the orchestration.\n\n## Install\n\n```bash\nnpm install @claude-flow/neural\n```\n\n> **Note (2026-05-16):** `@claude-flow/neural@3.0.0-alpha.9+` pins\n> `@ruvector/sona` to the exact known-good `0.1.5` because\n> `@ruvector/sona@0.1.6` shipped as an empty publish (README +\n> `package.json` only — no `index.js`, no native bins). Prior alpha.8\n> used `\"latest\"` and broke on every fresh install. The pin will\n> stay until `@ruvector/sona@0.1.7+` ships with content.\n\n## Standalone use (without the Ruflo CLI)\n\n```typescript\n// route a task across 8 specialized experts (MoE) — no other deps\nimport { getMoERouter } from '@claude-flow/neural';\n\nconst router = getMoERouter();\nawait router.initialize();\n\nconst decision = await router.route(\n  new Float32Array(384).fill(0.1),   // task embedding\n  { task: 'optimize-query', complexity: 0.7 },\n);\nconsole.log(decision.expert, decision.confidence);\n// → 'performance', 0.83  (or whichever expert wins)\n```\n\n## Quick start (recommended)\n\n`NeuralLearningSystem` is the high-level entry point — it wires `SONAManager`, `ReasoningBank`, and `PatternLearner` together so callers don't have to:\n\n```typescript\nimport { createNeuralLearningSystem } from '@claude-flow/neural';\n\nconst sys = createNeuralLearningSystem('balanced');\nawait sys.initialize();\n\n// Track a task\nconst id = sys.beginTask('Refactor auth middleware', 'code');\n\n// Record steps as the agent works (Float32Array embeddings)\nsys.recordStep(id, 'analyzed-imports', 0.8, embedding1);\nsys.recordStep(id, 'extracted-helpers',  0.9, embedding2);\n\n// Complete — fires distillation + pattern extraction automatically\nawait sys.completeTask(id, /* qualityScore */ 0.85);\n\n// Retrieve relevant memories for the next similar task\nconst memories = await sys.retrieveMemories(queryEmbedding, /* k */ 3);\nconst patterns = await sys.findPatterns(queryEmbedding, 3);\n\n// Periodic learning sweep (consolidation + EWC)\nawait sys.triggerLearning();\n\nconsole.log(sys.getStats());\n// → { sona: NeuralStats, reasoningBank: { ... }, patternLearner: { ... } }\n```\n\n## Lower-level API: SONA Manager\n\nFor callers that want to manage trajectories and patterns directly:\n\n```typescript\nimport { createSONAManager, type Trajectory } from '@claude-flow/neural';\n\nconst sona = createSONAManager('balanced');\nawait sona.initialize();\n\n// domain ∈ 'code' | 'creative' | 'reasoning' | 'chat' | 'math' | 'general'\nconst trajectoryId = sona.beginTrajectory('code-review-task', 'code');\n\nsona.recordStep(trajectoryId, 'analyze-code',     0.8, stateEmbedding);\nsona.recordStep(trajectoryId, 'generate-feedback', 0.9, nextStateEmbedding);\n\nconst trajectory: Trajectory = sona.completeTrajectory(trajectoryId, 0.85);\n\n// Query patterns\nconst matches = await sona.findSimilarPatterns(contextEmbedding, /* k */ 3);\n\n// Trigger consolidation manually\nawait sona.triggerLearning('manual');\nsona.consolidateEWC();\n```\n\n## Learning modes\n\n| Mode | Adaptation | Quality | Memory | Use case |\n|------|-----------:|--------:|-------:|----------|\n| **real-time** | <0.5ms | 70%+ | 25 MB | Production, low-latency |\n| **balanced** (default) | <18ms | 75%+ | 50 MB | General purpose |\n| **research** | <100ms | 95%+ | 100 MB | Deep exploration |\n| **edge** | <1ms | 80%+ | 5 MB | Resource-constrained |\n| **batch** | <50ms | 85%+ | 75 MB | High-throughput |\n\n```typescript\nawait sys.setMode('research'); // or directly: await sona.setMode('research')\n```\n\n## ReasoningBank + PatternLearner (separately accessible)\n\n`NeuralLearningSystem` composes them; you can also use them standalone:\n\n```typescript\nimport {\n  createReasoningBank,\n  createPatternLearner,\n  createSONALearningEngine,\n} from '@claude-flow/neural';\n\nconst bank = createReasoningBank();\nawait bank.storeTrajectory(trajectory);\nawait bank.judge(trajectory);\nconst distilled = await bank.distill(trajectory);\n\nconst learner = createPatternLearner();\nlearner.extractPattern(trajectory, distilled);\nconst matches = await learner.findMatches(queryEmbedding, 5);\n\nconst engine = createSONALearningEngine();\nconst adapted = await engine.adapt(input, /* domain */ 'code');\n```\n\n## RL algorithms (7 included)\n\nImports use the `Algorithm` suffix where applicable:\n\n```typescript\nimport {\n  PPOAlgorithm,         createPPO,         DEFAULT_PPO_CONFIG,\n  A2CAlgorithm,         createA2C,         DEFAULT_A2C_CONFIG,\n  DQNAlgorithm,         createDQN,         DEFAULT_DQN_CONFIG,\n  QLearning,            createQLearning,   DEFAULT_QLEARNING_CONFIG,\n  SARSAAlgorithm,       createSARSA,       DEFAULT_SARSA_CONFIG,\n  DecisionTransformer,  createDecisionTransformer, DEFAULT_DT_CONFIG,\n  CuriosityModule,      createCuriosity,   DEFAULT_CURIOSITY_CONFIG,\n} from '@claude-flow/neural';\n\nconst ppo = createPPO({ learningRate: 0.0003, epsilon: 0.2, valueCoef: 0.5 });\nconst dqn = createDQN({ learningRate: 0.001, gamma: 0.99, epsilon: 0.1, targetUpdateFreq: 100 });\n\n// Generic factory — pick algorithm by name\nimport { createAlgorithm, getDefaultConfig } from '@claude-flow/neural';\nconst algo = createAlgorithm('ppo', getDefaultConfig('ppo'));\n```\n\n## LoRA configuration\n\n```typescript\nconst config = sona.getLoRAConfig();\n// { rank: 4, alpha: 8, dropout: 0.05, targetModules: ['q_proj','v_proj','k_proj','o_proj'], microLoRA: false }\n\nconst weights = sona.initializeLoRAWeights('code-generation');\n```\n\n## EWC++ (Elastic Weight Consolidation)\n\nPrevents catastrophic forgetting when adapting to new domains:\n\n```typescript\nconst config = sona.getEWCConfig();\n// { lambda: 2000, decay: 0.9, fisherSamples: 100, minFisher: 1e-8, online: true }\n\n// After learning a new task, consolidate before moving on\nsona.consolidateEWC();\n```\n\n## Event system\n\n```typescript\nsys.addEventListener((event) => {\n  switch (event.type) {\n    case 'trajectory_started':  console.log(`Started: ${event.trajectoryId}`); break;\n    case 'trajectory_completed': console.log(`Quality: ${event.qualityScore}`); break;\n    case 'pattern_matched':     console.log(`Pattern ${event.patternId} matched`); break;\n    case 'learning_triggered':  console.log(`Learning: ${event.reason}`); break;\n    case 'mode_changed':        console.log(`${event.fromMode} → ${event.toMode}`); break;\n  }\n});\n```\n\n## Performance targets\n\n| Metric | Target | Typical |\n|--------|--------|---------|\n| Adaptation latency | <0.05 ms | 0.02 ms |\n| Pattern retrieval | <1 ms | 0.5 ms |\n| Learning step | <10 ms | 5 ms |\n| Quality improvement | +55% | +40–60% |\n| Memory overhead | <50 MB | 25–75 MB |\n\n## TypeScript types\n\n```typescript\nimport type {\n  // Core\n  SONAMode, SONAModeConfig, ModeOptimizations,\n  Trajectory, TrajectoryStep, TrajectoryVerdict, DistilledMemory,\n  Pattern, PatternMatch, PatternEvolution,\n\n  // RL\n  RLAlgorithm, RLConfig,\n  PPOConfig, DQNConfig, A2CConfig, QLearningConfig, SARSAConfig,\n  DecisionTransformerConfig, CuriosityConfig,\n\n  // Neural\n  LoRAConfig, LoRAWeights, EWCConfig, EWCState,\n  NeuralStats, NeuralEvent, NeuralEventListener,\n} from '@claude-flow/neural';\n```\n\n## Integration with `@claude-flow/cli`\n\nThe CLI's intelligence layer (`hooks_intelligence_*`, `neural_*` MCP tools, `/intelligence` dashboard) is the primary consumer. Phase 1 of the convergence (#1773) adds a thin bridge in `cli/src/memory/neural-package-bridge.ts` that lazy-loads `NeuralLearningSystem` so cli's intelligence handlers can call into the package surface alongside the existing local implementation. Future phases migrate cli's `LocalSonaCoordinator` and `LocalReasoningBank` to wrap this package's `SONALearningEngine` and `ReasoningBankAdapter`.\n\nIf you're building a Ruflo plugin that wants neural learning, depend on `@claude-flow/neural` directly rather than reaching into cli internals.\n\n## Dependencies\n\n- [`@claude-flow/memory`](../memory) — vector memory for patterns\n- `@ruvector/sona` — SONA learning engine\n\n## Related packages\n\n- [`@claude-flow/memory`](../memory) — memory backend\n- [`@claude-flow/cli`](../cli) — primary consumer + MCP tool surface\n- [`@claude-flow/cli-core`](../cli-core) — lite path (no neural; for plugin scripts)\n\n## License\n\nMIT\n","readmeFilename":"README.md"}