{"data":{"slug":"langchain-ai-langchain","name":"langchain","tagline":"The agent engineering platform.","github_url":"https://github.com/langchain-ai/langchain","owner":"langchain-ai","repo":"langchain","owner_avatar_url":"https://avatars.githubusercontent.com/u/126733545?v=4","primary_language":"Python","stars":146576,"forks":24509,"topics":["agents","ai","ai-agents","anthropic","chatgpt","deepagents","enterprise","framework","gemini","generative-ai","langchain","langgraph","llm","multiagent","open-source","openai","pydantic","python","rag","typescript"],"archived":false,"github_pushed_at":"2026-09-18T08:16:52+00:00","maintenance_label":"Very active","stars_delta_30d":2961,"url":"https://www.graphcanon.com/tools/langchain-ai-langchain","markdown_url":"https://www.graphcanon.com/tools/langchain-ai-langchain.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/langchain-ai-langchain","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=langchain-ai-langchain","description":"The agent engineering platform.","homepage_url":"https://docs.langchain.com/langchain/","license":"MIT","open_issues":541,"watchers":922,"ai_summary":"LangChain is a framework for building agents and LLM-powered applications, simplifying AI application development through interoperable components and third-party integrations.","readme_excerpt":"
\n \n \n \n \n \"LangChain\n \n \n
\n\n
\n

The agent engineering platform.

\n
\n\n
\n \"PyPI\n \"PyPI\n \"Version\"\n \"Twitter\n
\n\n
\n\nLangChain is a framework for building agents and LLM-powered applications. It helps you chain together interoperable components and third-party integrations to simplify AI application development — all while future-proofing decisions as the underlying technology evolves.\n\n> [!TIP]\n> Just getting started? Check out **[Deep Agents](http://docs.langchain.com/oss/python/deepagents/)** — a higher-level package built on LangChain for agents that have built-in capabilities for common usage patterns such as planning, subagents, file system usage, and more.\n\n## Quickstart\n\n```bash\nuv add langchain\n```\n\n```python\nfrom langchain.chat_models import init_chat_model\n\nmodel = init_chat_model(\"openai:gpt-5.5\")\nresult = model.invoke(\"Hello, world!\")\n```\n\nIf you're looking for more advanced customization or agent orchestration, check out [LangGraph](https://github.com/langchain-ai/langgraph), our framework for building controllable agent workflows.\n\nFor an equivalent JS/TS library, check out [LangChain.js](https://github.com/langchain-ai/langchainjs).\n\n> [!TIP]\n> For developing, debugging, and deploying AI agents and LLM applications, see [LangSmith](https://docs.langchain.com/langsmith/home).\n\n## LangChain ecosystem\n\nWhile the LangChain framework can be used standalone, it also integrates seamlessly with any LangChain product, giving developers a full suite of tools when building LLM applications.\n\n- **[Deep Agents](http://docs.langchain.com/oss/python/deepagents/)** — Build agents that can plan, use subagents, and leverage file systems for complex tasks\n- **[LangGraph](https://docs.langchain.com/oss/python/langgraph/overview)** — Build agents that can reliably handle complex tasks with our low-level agent orchestration framework\n- **[Integrations](https://docs.langchain.com/oss/python/integrations/providers/overview)** — Chat & embedding models, tools & toolkits, and more\n- **[LangSmith](https://www.langchain.com/langsmith)** — Agent evals, observability, and debugging for LLM apps\n- **[LangSmith Deployment](https://docs.langchain.com/langsmith/deployments)** — Deploy and scale agents with a purpose-built platform for long-running, stateful workflows\n\n## Why use LangChain?\n\nLangChain helps developers build applications powered by LLMs through a standard interface for models, embeddings, vector stores, and more.\n\n- **Real-time data augmentation** — Easily connect LLMs to diverse data sources and external/internal systems, drawing from LangChain's vast library of integrations with model providers, tools, vector stores, retrievers, and more\n- **Model interoperability** — Swap models in and out as your engineering team experiments to find the best choice for your application's needs. As the industry frontier evolves, adapt quickly — LangChain's abstractions keep you moving without losing momentum\n- **Rapid prototyping**","github_created_at":"2022-10-17T02:58:36+00:00","created_at":"2026-07-07T15:07:35.78142+00:00","updated_at":"2026-09-30T18:34:42.012945+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"},{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"}],"tags":[{"slug":"agents","name":"agents"},{"slug":"ai-agents","name":"ai-agents"},{"slug":"framework","name":"framework"},{"slug":"langchain","name":"langchain"},{"slug":"multiagent","name":"multiagent"},{"slug":"open-source","name":"open-source"},{"slug":"python","name":"python"},{"slug":"typescript","name":"typescript"}],"trust":{"provenance":{"is_fork":false,"github_id":552661142,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-18T08:26:20.336Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":30,"days_since_push":0,"last_release_at":"2026-09-17T22:24:57Z","stars_delta_30d":2961,"open_issues_delta_30d":78},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-09-18T08:26:22.823Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-18T08:26:19.192Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-09-18T08:26:19.192Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-09-18T08:26:19.192Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you need a framework that simplifies chaining together interoperable components and third-party integrations for AI application development.","If you are looking to build agents that can plan, use subagents, and leverage file systems for complex tasks with Deep Agents.","For developers who require a low-level agent orchestration framework to reliably handle complex tasks with LangGraph."],"when_not_to_use":["If you prefer a framework that does not offer built-in capabilities for common usage patterns such as planning and subagents, as LangChain's Deep Agents provide these features.","When you need a higher-level abstraction that does not require detailed agent orchestration, as LangChain's LangGraph is designed for low-level control over agent workflows."],"source":"enrich:decision_facts","observed_at":"2026-09-18T12:10:35.619Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"LangChain is a Python framework for building agents and LLM-powered applications, offering interoperable components and third-party integrations to simplify AI application development."}]}}