LangChain's framework for building stateful, multi-actor AI agent applications.
LangGraph is a framework from LangChain for building stateful, multi-actor applications with LLMs. It models agent workflows as graphs where nodes are functions and edges define the flow. Features include built-in persistence (checkpointing), human-in-the-loop support, streaming, and fault tolerance. Used to build everything from simple chatbots to complex multi-agent systems. Part of the LangChain ecosystem with deep integration with LangSmith for observability.