> ## Documentation Index
> Fetch the complete documentation index at: https://docs.langchain.com/llms.txt
> Use this file to discover all available pages before exploring further.

# How to add custom routes

When deploying agents to LangSmith Deployment, your server automatically exposes routes for creating runs and threads, interacting with the long-term memory store, managing configurable assistants, and other core functionality ([see all default API endpoints](/langsmith/server-api-ref)).

You can add custom routes by providing your own app object and passing its path in `langgraph.json` (for example, a [`Starlette`](https://www.starlette.io/applications/) app in Python or a [`Hono`](https://hono.dev/) app in TypeScript).

Defining a custom app object lets you add any routes you'd like, so you can do anything from adding a `/login` endpoint to writing an entire full-stack web-app, all deployed in a single Agent Server.

Below are examples for Python and TypeScript.

## Create app

Starting from an **existing** LangSmith application, add the following custom route code to your app file. If you are starting from scratch, you can create a new app from a template using the CLI.

<Tabs>
  <Tab title="Python">
    ```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
    langgraph new --template=new-langgraph-project-python my_new_project
    ```

    Once you have a LangGraph project, add the following app code:

    ```python {highlight={4}} theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
    # ./src/agent/webapp.py
    from fastapi import FastAPI

    app = FastAPI()


    @app.get("/hello")
    def read_root():
        return {"Hello": "World"}
    ```
  </Tab>

  <Tab title="TypeScript">
    ```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
    yarn create langgraph
    npm install hono
    ```

    Once you have a LangGraph project, add the following app code:

    ```typescript theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
    // ./src/custom-routes.ts
    import { Hono } from "hono";

    export const app = new Hono()
      .get("/custom/hello", (c) => {
        return c.json({ hello: "world" });
      })
      .post("/custom/webhook", async (c) => {
        const body = await c.req.json();
        return c.json({ received: true, payload: body });
      });
    ```

    The `hono` package must be available in your project dependencies.
  </Tab>
</Tabs>

## Configure `langgraph.json`

Add the following to your `langgraph.json` configuration file. Make sure the path points to the app instance you created in the [previous section](#create-app).

<Tabs>
  <Tab title="Python">
    ```json theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
    {
      "dependencies": ["."],
      "graphs": {
        "agent": "./src/agent/graph.py:graph"
      },
      "env": ".env",
      "http": {
        "app": "./src/agent/webapp.py:app"
      }
      // Other configuration options like auth, store, etc.
    }
    ```
  </Tab>

  <Tab title="TypeScript">
    ```json theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
    {
      "node_version": "20",
      "dependencies": ["."],
      "graphs": { "agent": "./src/agent.ts:graph" },
      "http": { "app": "./src/custom-routes.ts:app" },
      "env": ".env"
    }
    ```
  </Tab>
</Tabs>

## Start server

Test the server out locally:

<Tabs>
  <Tab title="Python">
    ```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
    langgraph dev --no-browser
    ```
  </Tab>

  <Tab title="TypeScript">
    ```bash theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
    npx @langchain/langgraph-cli@latest dev --no-browser
    ```
  </Tab>
</Tabs>

If you navigate to `localhost:2024/hello` in your browser (`2024` is the default development port), you should see the `/hello` endpoint returning a JSON response. For the TypeScript example, navigate to `localhost:2024/custom/hello`.

The TypeScript `http.app` configuration works in both local development with `langgraph dev` and Docker with `langgraph up`.

<Note>
  **Shadowing default endpoints**
  The routes you create in the app are given priority over the system defaults, meaning you can shadow and redefine the behavior of any default endpoint.
</Note>

## Deploying

You can deploy this app as-is to LangSmith or to your self-hosted platform.

## Next steps

Now that you've added a custom route to your deployment, you can use this same technique to further customize how your server behaves, such as defining [custom middleware](/langsmith/custom-middleware) and [custom lifespan events](/langsmith/custom-lifespan).

***

<div className="source-links">
  <Callout icon="terminal-2">
    [Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
  </Callout>

  <Callout icon="edit">
    [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/langsmith/custom-routes.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>
</div>