LangChain · Durable agents
LangGraph
Orchestrate stateful agent workflows with persistence, streaming, and human oversight.
- Languages
- Python, TypeScript
- API surface
- Graph orchestration SDK
- MCP capability
- MCP integration
APIs & SDKs
Build stateful graphs that combine deterministic functions with model-driven steps. Persistence, streaming and human intervention belong to the orchestration layer.
Explore the developer documentation ↗Integrations
LangGraph can use LangChain model and tool components, but does not require LangChain. LangSmith provides a separate tracing, evaluation and deployment platform.
View framework integration resources ↗MCP integration
MCP support
A LangChain tool integration is one route to MCP-backed tools in graph workflows. The linked Python guide documents MCPAdapter; LangGraph itself is the orchestration runtime.
Evidence scope: Python LangChain integration; confirm TypeScript separately. Documentation reviewed; runtime compatibility has not been tested.
Sources & review
Integration notes reviewed . Check the linked documentation for current package versions, language support and authentication requirements.
How we review directory entries →