agentic-aiCommunity canon

LangGraph

Stateful multi-agent orchestration for LLM applications

View on GitHub

What it solves

The state management problem in multi-agent systems: how you build agents that pass context across turns without losing the execution thread.

Overview

LangGraph extends LangChain with a graph-based execution model for building stateful, multi-actor applications. Core primitive: a directed graph where nodes are agent functions and edges are control flow, enabling loops, branching, and persistent state that vanilla chains cannot express.

Key facts

Language
Python
License
MIT
Maturity
Community canon
Maintainer
langchain-ai
Reviewed
2026-06-11

Where to start

Start here to see the agent loop pattern in working code.

examples/multi_agent/agent_executor.py

Technologies

langgraphlangchainpython

More in this domain