{"library":"deepagents","type":"library","category":null,"description":"Agent harness by LangChain built on LangGraph. Implements planning (write_todos tool), filesystem backends, and subagent delegation — the architecture behind Claude Code, Manus, and Deep Research. Returns a compiled LangGraph StateGraph. Released mid-2025. Current version: 0.4.12 (Mar 2026). Default model is Claude Sonnet (not GPT-4o). Requires LangChain core libraries.","language":"python","status":"active","version":"0.4.12","tags":["deepagents","langchain","langgraph","agents","python","planning","filesystem"],"last_verified":"Tue Jun 09","install":[{"cmd":"pip install deepagents","imports":["from deepagents import create_deep_agent\nfrom langchain.chat_models import init_chat_model\n\n# Custom model\nmodel = init_chat_model('openai:gpt-4o')\nagent = create_deep_agent(\n    model=model,\n    tools=[],\n    system_prompt='You are a research assistant.'\n)\n\n# invoke with messages dict — not plain string\nresult = agent.invoke({\n    'messages': [{'role': 'user', 'content': 'Research LangGraph'}]\n})\nprint(result['messages'][-1].content)"]},{"cmd":"pip install deepagents langchain-openai","imports":[]}],"homepage":"https://docs.langchain.com/oss/python/deepagents/overview","github":"https://github.com/langchain-ai/deepagents","docs":"https://reference.langchain.com/python/deepagents/","changelog":null,"pypi":"https://pypi.org/project/deepagents/","npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":{"summary":{"python_range":"3.10–3.9","success_rate":60,"avg_install_s":11.3,"avg_import_s":4.94,"wheel_type":"wheel"},"url":"https://checklist.day/v1/registry/deepagents/compatibility"}}