Last Updated: 3/7/2026

Docs by LangChain home page

Deep AgentsLangChainLangGraphIntegrationsLearnReferenceContribute

• Overview

Get started

• Install
• Quickstart
• Local server
• Changelog 
• Thinking in LangGraph
• Workflows + agents

Capabilities

• Persistence
• Durable execution
• Streaming
• Interrupts
• Time travel
• Memory
• Subgraphs

Production

• Application structure
• Test
• LangSmith Studio
• Agent Chat UI
• LangSmith Deployment
• LangSmith Observability

LangGraph APIs

• Runtime

Get started

Install LangGraph

To install the base LangGraph package:

Copy

pip install -U langgraph pip  install -U  langgraph

To use LangGraph you will usually want to access LLMs and define tools. You can do this however you see fit. One way to do this (which we will use in the docs) is to use LangChain. Install LangChain with:

Copy

pip install -U langchain pip  install -U  langchain# Requires Python 3.10+# Requires Python 3.10+

To work with specific LLM provider packages, you will need install them separately. Refer to the integrations page for provider-specific installation instructions.

Edit this page on GitHub  or file an issue .

Connect these docs to Claude, VSCode, and more via MCP for real-time answers.

Was this page helpful?

[LangGraph overview

Previous](/oss/python/langgraph/overview)Quickstart