Run a LangGraph app locally

This quickstart shows you how to set up a LangGraph application locally for testing and development.

Prerequisites

Before you begin, ensure you have an API key for LangSmith (free to sign up).

1. Install the LangGraph CLI

Python server

# Python >= 3.11 is required.

pip install -U "langgraph-cli[inmem]"

2. Create a LangGraph app 🌱

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

Python server

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:

Python server

cd path/to/your/app
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:

LANGSMITH_API_KEY=lsv2...

5. Launch LangGraph Server 🚀

Start the LangGraph API server locally:

Python server

langgraph dev

Sample output:

>    Ready!
>
>    - API: [http://localhost:2024](http://localhost:2024/)
>
>    - Docs: http://localhost:2024/docs
>
>    - Studio Web UI: https://smith.langchain.com/studio/?baseUrl=http://127.0.0.1:2024

The langgraph dev command starts LangGraph Server in an in-memory mode. This mode is suitable for development and testing purposes.

For production use, deploy LangGraph Server with a persistent storage backend. For more information, refer to the LangSmith hosting options.

6. Test the API

Python SDK (async)

1. Install the LangGraph Python SDK:

pip install langgraph-sdk

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

from langgraph_sdk import get_client
import asyncio

client = get_client(url="http://localhost:2024")

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

asyncio.run(main())

Next steps

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

• Studio is a specialized UI that you can connect to LangGraph API server to visualize, interact with, and debug your application locally. Try the Studio quickstart.
• Deploy on cloud with the quickstart guide.
• LangGraph Server API Reference: Explore the LangGraph Server API documentation.
• Python SDK Reference: Explore the Python SDK API Reference.
• JS/TS SDK Reference: Explore the JS/TS SDK API Reference.

---

Edit the source of this page on GitHub