Last Updated: 3/11/2026

Installation

Install LangGraph and its dependencies to start building stateful agents.

Install LangGraph

Python

Install the base LangGraph package:


# Using pip
pip install -U langgraph
 
# Using uv (faster alternative)
uv add langgraph

JavaScript/TypeScript

Install LangGraph for JavaScript/TypeScript:


# Using npm
npm install @langchain/langgraph @langchain/core
 
# Using pnpm
pnpm add @langchain/langgraph @langchain/core
 
# Using yarn
yarn add @langchain/langgraph @langchain/core
 
# Using bun
bun add @langchain/langgraph @langchain/core

Install LangChain (Optional)

While LangGraph can be used standalone, most examples use LangChain for LLM integrations and tool definitions.

Python


# Using pip (requires Python 3.10+)
pip install -U langchain
 
# Using uv
uv add langchain

JavaScript/TypeScript


# Using npm
npm install langchain
 
# Using pnpm
pnpm add langchain
 
# Using yarn
yarn add langchain
 
# Using bun
bun add langchain

Install LLM Provider Packages

To use specific LLM providers, install their integration packages:

Python Examples


# OpenAI
pip install langchain-openai
 
# Anthropic
pip install langchain-anthropic
 
# Google
pip install langchain-google-genai

JavaScript Examples


# OpenAI
npm install @langchain/openai
 
# Anthropic
npm install @langchain/anthropic
 
# Google
npm install @langchain/google-genai

For a complete list of integrations, see the LangChain integrations documentation .

Verify Installation

Python

Create a simple test script:


from langgraph.graph import StateGraph, START, END
from typing_extensions import TypedDict
 
class State(TypedDict):
    value: int
 
def add_one(state: State) -> dict:
    return {"value": state["value"] + 1}
 
graph = StateGraph(State)
graph.add_node("add_one", add_one)
graph.add_edge(START, "add_one")
graph.add_edge("add_one", END)
 
app = graph.compile()
result = app.invoke({"value": 0})
print(result)  # {'value': 1}

JavaScript/TypeScript

Create a simple test script:


import { StateGraph, StateSchema, START, END } from "@langchain/langgraph";
import { z } from "zod";
 
const State = new StateSchema({
  value: z.number(),
});
 
const graph = new StateGraph(State)
  .addNode("addOne", (state) => ({ value: state.value + 1 }))
  .addEdge(START, "addOne")
  .addEdge("addOne", END)
  .compile();
 
const result = await graph.invoke({ value: 0 });
console.log(result);  // { value: 1 }

Next Steps

Quickstart: Build your first calculator agent
Core Concepts: Understand state, nodes, and edges
Building Graphs: Learn the Graph API in depth

Troubleshooting

Python Version Requirements

LangGraph requires Python 3.9 or higher. LangChain requires Python 3.10 or higher.

Check your Python version:


python --version

Dependency Conflicts

If you encounter dependency conflicts, try creating a fresh virtual environment:


# Using venv
python -m venv langgraph-env
source langgraph-env/bin/activate  # On Windows: langgraph-env\Scripts\activate
pip install langgraph
 
# Using conda
conda create -n langgraph-env python=3.11
conda activate langgraph-env
pip install langgraph