LangGraph
Stateful multi-agent orchestration for LLM applications
View on GitHubWhat 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.pyTechnologies
More in this domain
AutoGen
Multi-agent conversation framework from Microsoft Research
How to coordinate multiple specialized agents toward a shared goal without writing low-level orchestration logic by hand.
CrewAI
Role-based multi-agent orchestration for collaborative task execution
The boilerplate problem in multi-agent setup: defining roles, delegation rules, and task routing without writing a custom orchestration graph.
OpenAI Agents SDK
Lightweight Python SDK for building production-grade AI agents
The bootstrapping problem: going from a one-shot prompt to a real agent loop with handoffs, tool execution, and tracing without writing infrastructure from scratch.