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).
uv for Python or npx for TypeScript.

1. 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
Node server

uvx --from langgraph-cli@latest langgraph new path/to/your/app --template new-langgraph-project-python

npx @langchain/langgraph-cli new path/to/your/app --template new-langgraph-project-js

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.

2. Install dependencies

Python server
Node server

cd path/to/your/app
uv sync --dev -U

cd path/to/your/app
yarn install

3. Launch Agent Server

Start the Agent Server locally:

Python server
Node server

uv run langgraph dev

npx @langchain/langgraph-cli 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 Agent Server in an in-memory mode. This mode is suitable for development and testing purposes.

For production use, deploy Agent Server with a persistent storage backend. For more information, refer to the LangSmith platform options.To understand when to use langgraph dev vs langgraph up, see the Local development & testing guide.

4. Test the API

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

Install the LangGraph Python SDK:

pip install langgraph-sdk

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())

Install the LangGraph Python SDK:

pip install langgraph-sdk

Send a message to the assistant (threadless run):

from langgraph_sdk import get_sync_client

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

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?",
        }],
    },
    stream_mode="messages-tuple",
):
    print(f"Receiving new event of type: {chunk.event}...")
    print(chunk.data)
    print("\n\n")

Install the LangGraph JS SDK:

npm install @langchain/langgraph-sdk

Send a message to the assistant (threadless run):

const { Client } = await import("@langchain/langgraph-sdk");

// only set the apiUrl if you changed the default port when calling langgraph dev
const client = new Client({ apiUrl: "http://localhost:2024"});

const streamResponse = client.runs.stream(
    null, // Threadless run
    "agent", // Assistant ID
    {
        input: {
            "messages": [
                { "role": "user", "content": "What is LangGraph?"}
            ]
        },
        streamMode: "messages-tuple",
    }
);

for await (const chunk of streamResponse) {
    console.log(`Receiving new event of type: ${chunk.event}...`);
    console.log(JSON.stringify(chunk.data));
    console.log("\n\n");
}

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

Next steps

Now that you have a LangGraph app running locally, you’re ready to deploy it: Choose a hosting option for LangSmith:

Cloud: Fastest setup, fully managed (recommended).
Hybrid: in your cloud, managed by LangChain.
Self-hosted: Full control in your infrastructure.

For more details, refer to the Platform setup comparison. Then deploy your app:

Deploy to Cloud quickstart: Quick setup guide.
Full Cloud setup guide: Comprehensive deployment documentation.

Explore features:

Studio: Visualize, interact with, and debug your application with the Studio UI. Try the Studio quickstart.
API References: LangSmith Deployment API, Python SDK, JS/TS SDK

Edit this page on GitHub or file an issue.

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

Configure app for deployment

Deployment guides

App development

Studio

Auth & access control

Server customization

Prerequisites

1. Create a LangGraph app

2. Install dependencies

3. Launch Agent Server

4. Test the API

Next steps

Configure app for deployment

Deployment guides

App development

Studio

Auth & access control

Server customization

​Prerequisites

​1. Create a LangGraph app

​2. Install dependencies

​3. Launch Agent Server

​4. Test the API

​Next steps

Prerequisites

1. Create a LangGraph app

2. Install dependencies

3. Launch Agent Server

4. Test the API

Next steps