LangGraph
LangChain's stateful-graph framework for building agents as explicit nodes, edges, and conditional branches.
Definition
LangGraph is LangChain's library for orchestrating agents as a directed graph of nodes with shared state, instead of an opaque agent loop. Each node is a function or LLM call; edges decide the next step based on state. LangGraph is the preferred LangChain stack for production-grade agents because the graph topology is inspectable and testable.
When to use
See also
- LangChain — Python and JavaScript framework for building LLM applications — chains, agents, memory, retrieval, and tool use.
- agent — An LLM-driven program that plans, calls tools, observes results, and loops until it reaches a goal.
Mentioned in
- Best AI Agent Framework for Node.js Developers in 2026
- Best AI Agent Framework for Python Developers in 2026
- Fix LangChain create_react_agent 'unexpected keyword argument prompt'
- Fix LangChain Output Parsing Errors (handle_parsing_errors=True)
- LangChain vs LangGraph: when to use each for AI agents
- LlamaIndex vs LangChain: which framework for RAG and agents?