{"id":30412011,"url":"https://github.com/langchain-ai/deepagents","last_synced_at":"2026-06-13T04:02:49.961Z","repository":{"id":306863479,"uuid":"1027384981","full_name":"langchain-ai/deepagents","owner":"langchain-ai","description":"The batteries-included agent harness.","archived":false,"fork":false,"pushed_at":"2026-06-06T00:39:23.000Z","size":143142,"stargazers_count":23962,"open_issues_count":107,"forks_count":3384,"subscribers_count":116,"default_branch":"main","last_synced_at":"2026-06-06T08:02:36.065Z","etag":null,"topics":["ai","deepagents","langchain","langgraph","python","typescript"],"latest_commit_sha":null,"homepage":"https://docs.langchain.com/deepagents","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/langchain-ai.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":".github/CODEOWNERS","security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":"AGENTS.md","dco":null,"cla":null}},"created_at":"2025-07-27T23:07:53.000Z","updated_at":"2026-06-06T08:01:35.000Z","dependencies_parsed_at":"2026-02-12T23:00:57.558Z","dependency_job_id":null,"html_url":"https://github.com/langchain-ai/deepagents","commit_stats":null,"previous_names":["hwchase17/claude-everything","hwchase17/deepagents","langchain-ai/deepagents"],"tags_count":156,"template":false,"template_full_name":null,"purl":"pkg:github/langchain-ai/deepagents","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/langchain-ai%2Fdeepagents","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/langchain-ai%2Fdeepagents/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/langchain-ai%2Fdeepagents/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/langchain-ai%2Fdeepagents/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/langchain-ai","download_url":"https://codeload.github.com/langchain-ai/deepagents/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/langchain-ai%2Fdeepagents/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34175928,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-10T02:00:07.152Z","response_time":89,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai","deepagents","langchain","langgraph","python","typescript"],"created_at":"2025-08-22T02:01:10.735Z","updated_at":"2026-06-13T04:02:49.956Z","avatar_url":"https://github.com/langchain-ai.png","language":"Python","funding_links":[],"categories":["Python","🤖 AI \u0026 Machine Learning","Runtimes, Harnesses \u0026 Reference Implementations","Phase 3: Build and Integrate","Reference Implementations","Agent Harness 🚀","🟢 Official LangGraph Projects 🦜","Agentic Frameworks","Agent Ecosystem","Personal Assistants \u0026 Conversational Agents","🧠 AI Applications \u0026 Platforms","AI Agent Frameworks","Repos","AI \u0026 LLM"],"sub_categories":["Developer Tools","Demo Harnesses","5. The Convergence: Harness-as-a-Service (HaaS)","🟩 Specialized Agent Libraries 🤖","Harness Engineering","Chatbots","Tools","Agents \u0026 Orchestration"],"readme":"\u003cdiv align=\"center\"\u003e\n  \u003ca href=\"https://docs.langchain.com/oss/python/deepagents/overview#deep-agents-overview\"\u003e\n    \u003cpicture\u003e\n      \u003csource media=\"(prefers-color-scheme: dark)\" srcset=\".github/images/logo-dark.svg\"\u003e\n      \u003csource media=\"(prefers-color-scheme: light)\" srcset=\".github/images/logo-light.svg\"\u003e\n      \u003cimg alt=\"Deep Agents Logo\" src=\".github/images/logo-dark.svg\" width=\"50%\"\u003e\n    \u003c/picture\u003e\n  \u003c/a\u003e\n\u003c/div\u003e\n\n\u003cdiv align=\"center\"\u003e\n  \u003ch3\u003eThe batteries-included agent harness.\u003c/h3\u003e\n\u003c/div\u003e\n\n\u003cdiv align=\"center\"\u003e\n  \u003ca href=\"https://opensource.org/licenses/MIT\" target=\"_blank\"\u003e\u003cimg src=\"https://img.shields.io/pypi/l/deepagents\" alt=\"PyPI - License\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://pypistats.org/packages/deepagents\" target=\"_blank\"\u003e\u003cimg src=\"https://img.shields.io/pepy/dt/deepagents\" alt=\"PyPI - Downloads\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://pypi.org/project/deepagents/#history\" target=\"_blank\"\u003e\u003cimg src=\"https://img.shields.io/pypi/v/deepagents?label=%20\" alt=\"Version\"\u003e\u003c/a\u003e\n  \u003ca href=\"https://x.com/langchain_oss\" target=\"_blank\"\u003e\u003cimg src=\"https://img.shields.io/twitter/url/https/twitter.com/langchain_oss.svg?style=social\u0026label=Follow%20%40LangChain\" alt=\"Twitter / X\"\u003e\u003c/a\u003e\n\u003c/div\u003e\n\n\u003cbr\u003e\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\u003e [!NOTE]\n\u003e **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\u003e [!TIP]\n\u003e 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","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flangchain-ai%2Fdeepagents","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flangchain-ai%2Fdeepagents","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flangchain-ai%2Fdeepagents/lists"}