{"_id":"@anouar-bm/deepagents","name":"@anouar-bm/deepagents","dist-tags":{"latest":"1.10.2"},"versions":{"1.10.2":{"name":"@anouar-bm/deepagents","version":"1.10.2","private":false,"description":"Deep Agents - a library for building controllable AI agents with LangGraph","main":"./dist/index.cjs","module":"./dist/index.js","types":"./dist/index.d.ts","type":"module","scripts":{"build":"tsdown","clean":"rm -rf dist/ .tsdown/","dev":"tsc --watch","typecheck":"tsc --noEmit","prepublishOnly":"pnpm build","test":"vitest run","test:unit":"vitest run","test:int":"vitest run --mode int","test:watch":"vitest","test:ui":"vitest --ui","test:coverage":"vitest run --coverage"},"repository":{"type":"git","url":"git+https://github.com/langchain-ai/deepagentsjs.git"},"keywords":["ai","agents","langgraph","langchain","typescript","llm"],"author":{"name":"LangChain"},"license":"MIT","bugs":{"url":"https://github.com/langchain-ai/deepagentsjs/issues"},"homepage":"https://github.com/langchain-ai/deepagentsjs#readme","dependencies":{"@langchain/core":"^1.1.44","@langchain/langgraph":"^1.3.2","@langchain/langgraph-sdk":"^1.9.1","fast-glob":"^3.3.3","langchain":"^1.4.2","micromatch":"^4.0.8","yaml":"^2.8.2","zod":"^4.3.6"},"devDependencies":{"@langchain/anthropic":"^1.3.26","@langchain/langgraph-checkpoint":"^1.0.2","@langchain/openai":"^1.4.1","@langchain/sandbox-standard-tests":"workspace:*","@langchain/tavily":"^1.2.0","@tsconfig/recommended":"^1.0.13","@types/micromatch":"^4.0.10","@types/node":"^25.2.3","@vitest/coverage-v8":"^4.0.18","@vitest/ui":"^4.0.18","dotenv":"^17.2.4","tsdown":"^0.21.4","tsx":"^4.21.0","typescript":"^6.0.2","vitest":"^4.0.18"},"exports":{".":{"import":{"types":"./dist/index.d.ts","default":"./dist/index.js"},"require":{"types":"./dist/index.d.cts","default":"./dist/index.cjs"}},"./package.json":"./package.json"},"peerDependencies":{"langsmith":"^0.7.1"},"gitHead":"3d1cb90d8de0ae48cbe5d366f5a349ee016b8876","_id":"@anouar-bm/deepagents@1.10.2","_nodeVersion":"26.0.0","_npmVersion":"11.15.0","dist":{"integrity":"sha512-eSc/e+s16F0SGZh7KUlT28cFTgAh1Q7sD3cE/oK6mAZLNNW86H+tcm/TfcN6ofxDjq3dIahFBVSEAfkjzEbhzA==","shasum":"54328a89edce6061e4f4b5650b7c7745c9fd5cb9","tarball":"https://registry.npmjs.org/@anouar-bm/deepagents/-/deepagents-1.10.2.tgz","fileCount":9,"unpackedSize":2282414,"signatures":[{"keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U","sig":"MEUCIBUA6zSgc0/ccenod7LSM12mvR5D32depOr45FBVBSXwAiEAvYX+h2iLibJ2aA8M7kIsv8cpr57wMQJqTxv0CfXroHA="}]},"_npmUser":{"name":"anouar-bm","email":"anouarbnmoussa@gmail.com"},"directories":{},"maintainers":[{"name":"anouar-bm","email":"anouarbnmoussa@gmail.com"}],"_npmOperationalInternal":{"host":"s3://npm-registry-packages-npm-production","tmp":"tmp/deepagents_1.10.2_1779650816812_0.9138701410153578"},"_hasShrinkwrap":false}},"time":{"created":"2026-05-24T19:26:56.581Z","1.10.2":"2026-05-24T19:26:56.956Z","modified":"2026-05-24T19:26:57.117Z"},"maintainers":[{"name":"anouar-bm","email":"anouarbnmoussa@gmail.com"}],"description":"Deep Agents - a library for building controllable AI agents with LangGraph","homepage":"https://github.com/langchain-ai/deepagentsjs#readme","keywords":["ai","agents","langgraph","langchain","typescript","llm"],"repository":{"type":"git","url":"git+https://github.com/langchain-ai/deepagentsjs.git"},"author":{"name":"LangChain"},"bugs":{"url":"https://github.com/langchain-ai/deepagentsjs/issues"},"license":"MIT","readme":"
\n \n \n \n \n \"Deep\n \n \n
\n\n
\n

The batteries-included agent harness.

\n
\n\n
\n \"npm\n \"License:\n \"TypeScript\"\n \"Twitter\n
\n\n
\n\nDeep Agents is an agent harness. An opinionated, ready-to-run agent out of the box. Instead of wiring prompts, tools, and context management yourself, you get a working agent immediately and customize what you need.\n\n**What's included:**\n\n- **Planning** — `write_todos` for task breakdown and progress tracking\n- **Filesystem** — `read_file`, `write_file`, `edit_file`, `ls`, `glob`, `grep` for working memory\n- **Sub-agents** — `task` for delegating work with isolated context windows\n- **Smart defaults** — built-in prompt and middleware that make these tools useful out of the box\n- **Context management** — file-based workflows to keep long tasks manageable\n\n> [!NOTE]\n> Looking for the Python package? See [langchain-ai/deepagents](https://github.com/langchain-ai/deepagents).\n\n## Quickstart\n\n```bash\nnpm install deepagents\n# or\npnpm add deepagents\n# or\nyarn add deepagents\n```\n\n```typescript\nimport { createDeepAgent } from \"deepagents\";\n\nconst agent = createDeepAgent();\n\nconst result = await agent.invoke({\n messages: [\n {\n role: \"user\",\n content: \"Research LangGraph and write a summary in summary.md\",\n },\n ],\n});\n```\n\nThe agent can plan, read/write files, and manage longer tasks with sub-agents and filesystem tools.\n\n> [!TIP]\n> For developing, debugging, and deploying AI agents and LLM applications, see [LangSmith](https://docs.langchain.com/langsmith/home).\n\n## Customization\n\nAdd tools, swap models, and customize prompts as needed:\n\n```typescript\nimport { ChatOpenAI } from \"@langchain/openai\";\nimport { createDeepAgent } from \"deepagents\";\n\nconst agent = createDeepAgent({\n model: new ChatOpenAI({ model: \"gpt-5\", temperature: 0 }),\n tools: [myCustomTool],\n systemPrompt: \"You are a research assistant.\",\n});\n```\n\nSee the [JavaScript Deep Agents docs](https://docs.langchain.com/oss/javascript/deepagents/overview) for full configuration options.\n\n## LangGraph Native\n\n`createDeepAgent` returns a compiled [LangGraph](https://docs.langchain.com/oss/javascript/langgraph/overview) graph, so you can use streaming, Studio, checkpointers, and other LangGraph features.\n\n## Why Use It\n\n- **100% open source** — MIT licensed and extensible\n- **Provider agnostic** — works with tool-calling chat models\n- **Built on LangGraph** — production runtime with streaming and persistence\n- **Batteries included** — planning, file access, sub-agents, and defaults out of the box\n- **Fast to start** — install and run with sensible defaults\n- **Easy to customize** — add tools/models/prompts when you need to\n\n---\n\n## Documentation\n\n- [docs.langchain.com](https://docs.langchain.com/oss/javascript/deepagents/overview) - Concepts and guides\n- [Examples](/examples) - Working agents and patterns\n- [LangChain Forum](https://forum.langchain.com) - Community discussion and support\n\n## Security\n\nDeep Agents follows a \"trust the LLM\" model. The agent can do anything its tools allow. Enforce boundaries at the tool/sandbox level, not by expecting the model to self-police. See the [security policy](https://github.com/langchain-ai/deepagentsjs?tab=security-ov-file) for more information.\n","readmeFilename":"README.md","_rev":"1-c286650afc5fe13bebd56a1623570b99"}