{ "markdown": "
\n \n \n \n \n \"Deep\n \n \n
\n\n
\n

The batteries-included agent harness.

\n
\n\n
\n \"PyPI\n \"PyPI\n \"Version\"\n \"Twitter\n
\n\n
\n\nDeep Agents is an open source agent harness — an opinionated agent that runs out of the box. Extend, override, or replace any piece.\n\n**Principles:**\n\n- **Opinionated** — defaults tuned for long-horizon, multi-step work\n- **Extensible** — override or replace any piece without forking\n- **Model-agnostic** — works with any LLM that supports tool calling: frontier, open-weight, or local\n- **Production-ready** — built on LangGraph (streaming, persistence, checkpointing) with first-class tracing, evaluation, and deployment via LangSmith\n\n**Features include:**\n\n- **Sub-agents** — delegate tasks to agents with isolated context windows\n- **Filesystem** — read, write, edit, or search over pluggable local, sandboxed, or remote backends\n- **Context management** — summarize long threads and offload tool outputs to disk\n- **Shell access** — run commands in your sandbox of choice\n- **Persistent memory** — pluggable state and store backends for cross-session recall\n- **Human-in-the-loop** — approve, edit, or reject tool calls before they run\n- **Skills** — reusable behaviors the agent can load on demand\n- **Tools** — bring your own functions or any MCP server\n\nDeep Agents is available as a JavaScript/TypeScript library — see [deepagents.js](https://github.com/langchain-ai/deepagentsjs).\n\n> [!NOTE]\n> **Deep Agents Code** — a pre-built coding agent in your terminal, similar to Claude Code or Cursor, powered by any LLM. Install with `curl -LsSf https://langch.in/dcode | bash`. See the [documentation](https://docs.langchain.com/deepagents-code) for the full feature set.\n\n## Quickstart\n\n```bash\nuv add deepagents\n```\n\n```python\nfrom deepagents import create_deep_agent\n\nagent = create_deep_agent(\n model=\"openai:gpt-5.5\",\n tools=[my_custom_tool],\n system_prompt=\"You are a research assistant.\",\n)\nresult = agent.invoke({\"messages\": \"Research LangGraph and write a summary\"})\n```\n\nThe agent can plan, read/write files, and manage its own context. Add your own tools, swap models, customize prompts, configure sub-agents, and more. See the [documentation](https://docs.langchain.com/oss/python/deepagents/overview) for full details.\n\n> [!TIP]\n> For developing, debugging, and deploying AI agents and LLM applications, see [LangSmith](https://docs.langchain.com/langsmith/home).\n\n## FAQ\n\n### How is this different from LangGraph or LangChain?\n\nLangGraph is the graph runtime. LangChain's `create_agent` is a minimal agent harness on top of it. Deep Agents is a more opinionated harness on top of `create_agent` — same building blocks, but with filesystem, sub-agents, context management, and skills bundled in. For how the three relate, see the [LangChain ecosystem overview](https://docs.langchain.com/oss/python/concepts/products).\n\n### Does this work with open-weight or local models?\n\nYes. Any model that supports tool calling works — frontier APIs (OpenAI, Anthropic, Google), open-weight models hosted on providers like Baseten or Fireworks, and self-hosted models via Ollama, vLLM, or llama.cpp. Use any [LangChain chat model](https://docs.langchain.com/oss/python/langchain/models).\n\n### Can I use this in production?\n\nYes! Deep Agents is built on LangGraph, designed for production agent deployments. Pair it with [LangSmith](https://docs.langchain.com/langsmith/home) for tracing, evaluation, and monitoring. See [Going to production](https://docs.langchain.com/oss/python/deepagents/going-to-production) for the full guide.\n\n### When should I use Deep Agents vs. LangChain or LangGraph directly?\n\nAll three are layers in the same stack — see the [LangChain ecosystem overview](https://docs.langchain.com/oss/python/concepts/products) for how they relate. Use **Deep Agents** when you want the full harness — planning, context management, delegation — out of the box. Use [**LangChain's `create_agent`**](https://docs.langchain.com/oss/python/langchain/agents) when you want a lighter harness without the bundled middleware. Drop to [**LangGraph**](https://docs.langchain.com/oss/python/langgraph/overview) when the agent loop itself isn't the right shape and you need a custom graph.\n\nThe layers compose: any LangGraph `CompiledStateGraph` can be passed in as a sub-agent to a Deep Agent, so custom orchestration plugs in alongside the harness's defaults.\n\n---\n\n## Resources\n\n- [Examples](examples/) — working agents and patterns\n- [Documentation](https://docs.langchain.com/oss/python/deepagents/overview) — conceptual overviews and guides\n- [LangChain ecosystem overview](https://docs.langchain.com/oss/python/concepts/products) — how Deep Agents, LangChain, LangGraph, and LangSmith fit together\n- [API reference](https://reference.langchain.com/python/deepagents/) — complete reference for all public classes, functions, and types\n- [Discussions](https://forum.langchain.com/c/oss-product-help-lc-and-lg/deep-agents/18) — community forum for technical questions, ideas, and feedback\n- [LangChain Academy](https://academy.langchain.com/) — Comprehensive, free courses on LangChain libraries and products, made by the LangChain team.\n- [Contributing Guide](https://docs.langchain.com/oss/python/contributing/overview) — how to contribute and find good first issues\n- [Code of Conduct](https://github.com/langchain-ai/langchain/?tab=coc-ov-file) — community guidelines and standards\n\n---\n\n## Acknowledgements\n\nInspired by Claude Code: an attempt to identify what makes it general-purpose, and push that further.\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/deepagents?tab=security-ov-file) for more information.\n", "bytes": 6924, "sha": "c404867a799a46fc6b26ac0d3824eb61135007b0e93793b07819621b9405fda1", "repo_slug": "langchain-ai/deepagents", "fonte": "repo", "truncated": false, "api": "https://agentalog.com/api/listings/skl_langchain_ai_deepagents_langgraph_docs_db6a628c/readme" }