Design agents with control

Add human oversight and create stateful, scalable workflows with AI agents.

Customize your agent runtime with LangGraph

LangGraph provides control for custom agent and multi-agent workflows, seamless human-in-the-loop interactions, and native streaming support for enhanced agent reliability and execution.

About LangGraph
001
002
003
004

Build the right cognitive architecture for your application

Identify and implement the best prompting strategies 
and architectures so that your LLMs perform as intended.

Go to Docs
001

Plan-and-execute

002

Multi-agent

003

Critique Revise

004

ReAct

005

Self-ask

Tools for every task

LangChain offers an extensive library of off-the-shelf tools 
and an intuitive framework for customizing your own.

Autonomous, 
but well‑behaved

Go to Docs

Debugging agents got you down? LangSmith can help.

LangSmith gives you the explainability to understand why your agents go off track and how to get them humming again.

Explore LangSmith
001
End-to-end trace observability
002
Tool selection visibility
003
Playground with prompt, model, and tool definition variability
004
Cost, latency, and error tracking
005
LLM evaluators for agent runs

Interested in becoming a LangChain Ambassador?

Start by hosting a meetup, building a digital community, or creating educational content - and share it with us in our Community Slack!