{"id":"langgraph","name":"LangGraph","maker":"LangChain","url":"https://www.langchain.com/langgraph","repo":"langchain-ai/langgraph","docs":"https://docs.langchain.com/oss/python/langgraph/overview","package":"pypi:langgraph","summary":"A library for building agents as graphs of steps that keep saved state, in Python and TypeScript.","details":"LangGraph models an agent as nodes and edges over a shared state, with checkpointing, human-in-the-loop pauses and streaming. It is a library in Python, with a separate TypeScript version. It works with any model through LangChain integrations and can run on its own or alongside LangChain's hosted deployment and tracing products.","open_source":true,"hosted":false,"speaks":["mcp"],"also":["workflow"],"verified":"2026-11-15","category":"frameworks","category_name":"Agent frameworks and SDKs","page":"https://modelmoot.com/tools/langgraph","reviewed":"2026-11-15","checked":{"at":"2026-11-15T14:03:44.997Z","address_answers":true},"note":"Descriptions are the site's own. Facts under \"checked\" were read automatically from the tool's address and public repository."}