{"data":{"slug":"langchain-ai-langgraph","name":"langgraph","tagline":"Low-level orchestration framework for building stateful agents","github_url":"https://github.com/langchain-ai/langgraph","owner":"langchain-ai","repo":"langgraph","owner_avatar_url":"https://avatars.githubusercontent.com/u/126733545?v=4","primary_language":"Python","stars":41866,"forks":7073,"topics":["agents","ai","ai-agents","chatgpt","deepagents","enterprise","framework","gemini","generative-ai","langchain","langgraph","llm","multiagent","open-source","openai","pydantic","python","rag"],"archived":false,"github_pushed_at":"2026-09-18T04:34:40+00:00","maintenance_label":"Very active","stars_delta_30d":3514,"url":"https://www.graphcanon.com/tools/langchain-ai-langgraph","markdown_url":"https://www.graphcanon.com/tools/langchain-ai-langgraph.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/langchain-ai-langgraph","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=langchain-ai-langgraph","description":"Build resilient agents.","homepage_url":"https://docs.langchain.com/oss/python/langgraph/","license":"MIT","open_issues":794,"watchers":184,"ai_summary":"LangGraph is a framework for building, managing, and deploying long-running, stateful agents. It supports durable execution, human-in-the-loop oversight, and comprehensive memory management.","readme_excerpt":"
\n \n \n \n \n \"LangGraph\n \n \n
\n\n
\n

Low-level orchestration framework for building stateful agents.

\n
\n\n
\n \"PyPI\n \"PyPI\n \"Version\"\n \"Twitter\n
\n\n
\n\nTrusted by companies shaping the future of agents – including Klarna, Replit, Elastic, and more – LangGraph is a low-level orchestration framework for building, managing, and deploying long-running, stateful agents.\n\n```bash\npip install -U langgraph\n```\n\n> [!TIP]\n> If you're looking to quickly build agents, check out **[Deep Agents](https://docs.langchain.com/oss/python/deepagents/overview)** — a higher-level package built on LangGraph for agents that can plan, use subagents, and leverage file systems for complex tasks.\n\nFor an equivalent JS/TS library, check out [LangGraph.js](https://github.com/langchain-ai/langgraphjs) and the [JS docs](https://docs.langchain.com/oss/javascript/langgraph/overview).\n\n## Why use LangGraph?\n\nLangGraph provides low-level supporting infrastructure for *any* long-running, stateful workflow or agent:\n\n- **[Durable execution](https://docs.langchain.com/oss/python/langgraph/durable-execution)** — Build agents that persist through failures and can run for extended periods, automatically resuming from exactly where they left off.\n- **[Human-in-the-loop](https://docs.langchain.com/oss/python/langgraph/interrupts)** — Seamlessly incorporate human oversight by inspecting and modifying agent state at any point during execution.\n- **[Comprehensive memory](https://docs.langchain.com/oss/python/langgraph/memory)** — Create truly stateful agents with both short-term working memory for ongoing reasoning and long-term persistent memory across sessions.\n- **[Debugging with LangSmith](https://www.langchain.com/langsmith)** — Gain deep visibility into complex agent behavior with visualization tools that trace execution paths, capture state transitions, and provide detailed runtime metrics.\n- **[Production-ready deployment](https://docs.langchain.com/langsmith/deployments)** — Deploy sophisticated agent systems confidently with scalable infrastructure designed to handle the unique challenges of stateful, long-running workflows.\n\n> [!TIP]\n> For developing, debugging, and deploying AI agents and LLM applications, see [LangSmith](https://docs.langchain.com/langsmith/home).\n\n## LangGraph ecosystem\n\nWhile LangGraph can be used standalone, it also integrates seamlessly with any LangChain product, giving developers a full suite of tools for building agents.\n\nTo improve your LLM application development, pair LangGraph with:\n\n- [Deep Agents](https://docs.langchain.com/oss/python/deepagents/overview) – Build agents that can plan, use subagents, and leverage file systems for complex tasks.\n- [LangChain](https://docs.langchain.com/oss/python/langchain/overview) – Provides integrations and composable components to streamline LLM application development.\n- [LangSmith](https://www.langchain.com/langsmith) – Helpful for agent evals and observability. Debug poor-performing LLM app runs, evaluate age","github_created_at":"2023-08-09T18:33:12+00:00","created_at":"2026-07-07T15:07:44.079562+00:00","updated_at":"2026-09-20T04:28:27.512296+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"}],"tags":[{"slug":"agents","name":"agents"},{"slug":"ai-agents","name":"ai-agents"},{"slug":"framework","name":"framework"},{"slug":"langchain","name":"langchain"},{"slug":"langgraph","name":"langgraph"},{"slug":"multiagent","name":"multiagent"},{"slug":"open-source","name":"open-source"},{"slug":"python","name":"python"}],"trust":{"provenance":{"is_fork":false,"github_id":676672661,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-18T08:06:51.267Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":12,"days_since_push":0,"last_release_at":"2026-08-27T21:25:36Z","stars_delta_30d":3514,"open_issues_delta_30d":147},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-09-18T08:06:54.211Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-18T08:06:50.197Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-09-18T08:06:50.197Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-09-18T08:06:50.197Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you need to build agents that can persist through failures and resume from where they left off, ensuring durable execution.","If your project requires seamless human oversight, allowing for inspection and modification of agent state at any point during execution.","For creating stateful agents with both short-term working memory and long-term persistent memory across sessions.","When you require deep visibility into complex agent behavior, including tracing execution paths and capturing state transitions with debugging tools like LangSmith."],"when_not_to_use":["If you are looking for a higher-level package that simplifies the process of building agents with planning and subagent capabilities, consider Deep Agents instead.","For projects that do not require long-running, stateful workflows, LangGraph's features may be overkill and a simpler framework might be more appropriate.","If your project is primarily focused on JavaScript or TypeScript, LangGraph.js might be a better fit, as LangGraph is primarily designed for Python environments."],"source":"enrich:decision_facts","observed_at":"2026-09-18T11:48:19.574Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"LangGraph is a low-level orchestration framework for building, managing, and deploying long-running, stateful agents, offering durable execution, human-in-the-loop oversight, and comprehensive memory management."}]}}