Skip to Content
Local Server

Last Updated: 3/7/2026

Docs by LangChain home page

Deep AgentsLangChainLangGraphIntegrationsLearnReferenceContribute

Get started
Capabilities
Production
LangGraph APIs

Get started

Run a local server

This guide shows you how to run a LangGraph application locally.

​ Prerequisites

Before you begin, ensure you have the following:

​ 1. Install the LangGraph CLI

Copy

# Python >= 3.11 is required.# Python >= 3.11 is required.pip install -U "langgraph-cli[inmem]" pip  install -U "langgraph-cli[inmem]"

​ 2. Create a LangGraph app

Create a new app from the new-langgraph-project-python template. This template demonstrates a single-node application you can extend with your own logic.

Copy

langgraph new path/to/your/app --template new-langgraph-project-python langgraph  new path/to/your/app --template new-langgraph-project-python

Additional templates If you use langgraph new without specifying a template, you will be presented with an interactive menu that will allow you to choose from a list of available templates.

​ 3. Install dependencies

In the root of your new LangGraph app, install the dependencies in edit mode so your local changes are used by the server:

Copy

cd path/to/your/app cd path/to/your/apppip install -e . pip  install -e .

​ 4. Create a .env file

You will find a .env.example in the root of your new LangGraph app. Create a .env file in the root of your new LangGraph app and copy the contents of the .env.example file into it, filling in the necessary API keys:

Copy

LANGSMITH_API_KEY=lsv2... LANGSMITH_API_KEY =lsv2...

​ 5. Launch Agent server

Start the LangGraph API server locally:

Copy

langgraph dev langgraph  dev

Sample output:

Copy

INFO:langgraph_api.cli:INFO:langgraph_api.cli:   Welcome to  Welcome to  ╦ ┌─┐┌┐┌┌─┐╔═╗┬─┐┌─┐┌─┐┬ ┬ ╦ ┌─┐┌┐┌┌─┐╔═╗┬─┐┌─┐┌─┐┬ ┬ ║ ├─┤││││ ┬║ ╦├┬┘├─┤├─┘├─┤ ║ ├─┤││││ ┬║ ╦├┬┘├─┤├─┘├─┤ ╩═╝┴ ┴┘└┘└─┘╚═╝┴└─┴ ┴┴ ┴ ┴ ╩═╝┴ ┴┘└┘└─┘╚═╝┴└─┴ ┴┴ ┴ ┴  - 🚀 API: http://127.0.0.1:2024 - 🚀 API: http://127.0.0.1:2024 - 🎨 Studio UI: https://smith.langchain.com/studio/?baseUrl=http://127.0.0.1:2024 - 🎨 Studio UI: https://smith.langchain.com/studio/?baseUrl=http://127.0.0.1:2024 - 📚 API Docs: http://127.0.0.1:2024/docs - 📚 API Docs: http://127.0.0.1:2024/docs This in-memory server is designed for development and testing.This in-memory server is designed for development and testing.For production use, please use LangSmith Deployment.For production use, please use LangSmith Deployment.

The langgraph dev command starts Agent Server in an in-memory mode. This mode is suitable for development and testing purposes. For production use, deploy Agent Server with access to a persistent storage backend. For more information, see the Platform setup overview.

​ 6. Test your application in Studio

Studio is a specialized UI that you can connect to LangGraph API server to visualize, interact with, and debug your application locally. Test your graph in Studio by visiting the URL provided in the output of the langgraph dev command:

Copy

> - LangGraph Studio Web UI: https://smith.langchain.com/studio/?baseUrl=http://127.0.0.1:2024> - LangGraph Studio Web UI: https://smith.langchain.com/studio/?baseUrl=http://127.0.0.1:2024

For an Agent Server running on a custom host/port, update the baseUrl query parameter in the URL. For example, if your server is running on http://myhost:3000:

Copy

https://smith.langchain.com/studio/?baseUrl=http://myhost:3000https://smith.langchain.com/studio/?baseUrl=http://myhost:3000

Safari compatibility

Use the --tunnel flag with your command to create a secure tunnel, as Safari has limitations when connecting to localhost servers:

Copy

langgraph dev --tunnel langgraph  dev --tunnel

​ 7. Test the API

  • Python SDK (async)
  • Python SDK (sync)
  • Rest API

  1. Install the LangGraph Python SDK:

    Copy

    pip install langgraph-sdk pip  install langgraph-sdk

  2. Send a message to the assistant (threadless run):

    Copy

    from langgraph_sdk import get_client from  langgraph_sdk import  get_client import asyncio import  asyncio client = get_client(url="http://localhost:2024") client = get_client(url ="http://localhost:2024") async def main(): async  def  main(): async for chunk in client.runs.stream( async  for  chunk in client.runs.stream( None, # Threadless run  None, # Threadless run "agent", # Name of assistant. Defined in langgraph.json.  "agent", # Name of assistant. Defined in langgraph.json. input={ input ={ "messages": [{ "messages": [{ "role": "human",  "role": "human", "content": "What is LangGraph?",  "content": "What is LangGraph?", }], }], }, }, ): ): print(f"Receiving new event of type: {chunk.event}...")  print(f"Receiving new event of type: {chunk.event}...") print(chunk.data)  print(chunk.data) print("\n\n")  print(" \n\n ") asyncio.run(main())asyncio.run(main())

  3. Install the LangGraph Python SDK:

    Copy

    pip install langgraph-sdk pip  install langgraph-sdk

  4. Send a message to the assistant (threadless run):

    Copy

    from langgraph_sdk import get_sync_client from  langgraph_sdk import  get_sync_client client = get_sync_client(url="http://localhost:2024") client = get_sync_client(url ="http://localhost:2024") for chunk in client.runs.stream(for  chunk in client.runs.stream( None, # Threadless run  None, # Threadless run "agent", # Name of assistant. Defined in langgraph.json.  "agent", # Name of assistant. Defined in langgraph.json. input={ input ={ "messages": [{ "messages": [{ "role": "human",  "role": "human", "content": "What is LangGraph?",  "content": "What is LangGraph?", }], }], }, }, stream_mode="messages-tuple",  stream_mode ="messages-tuple",):): print(f"Receiving new event of type: {chunk.event}...")  print(f"Receiving new event of type: {chunk.event}...") print(chunk.data)  print(chunk.data) print("\n\n")  print(" \n\n ")

Copy

curl -s --request POST \ curl -s --request  POST  \ --url "http://localhost:2024/runs/stream" \ --url "http://localhost:2024/runs/stream"  \ --header 'Content-Type: application/json' \ --header 'Content-Type: application/json'  \ --data "{ --data "{ \"assistant_id\": \"agent\",  \" assistant_id \": \" agent \", \"input\": { \" input \": { \"messages\": [ \" messages \": [ { { \"role\": \"human\",  \" role \": \" human \", \"content\": \"What is LangGraph?\"  \" content \": \" What is LangGraph? \" } } ] ] }, }, \"stream_mode\": \"messages-tuple\"  \" stream_mode \": \"messages-tuple \" }" }"

​ Next steps

Now that you have a LangGraph app running locally, take your journey further by exploring deployment and advanced features:

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?

QuickstartChangelog

IndexUse Graph Api