> ## Documentation Index
> Fetch the complete documentation index at: https://langchain-5e9cc07a-preview-devupd-1765394015-eccef47.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Call agents from code

> Invoke Agent Builder agents from Python or JavaScript using the LangGraph SDK.

You can invoke Agent Builder agents from your applications using the LangGraph SDK. You can use all the same API methods as you would with any other LangGraph deployment.

## Authentication

To authenticate with the deployment your Agent Builder agents are running on, you must provide a personal access token (PAT) API key tied to your user to the `api_key` arg when instantiating the LangGraph SDK client, or via the `X-API-Key` header. Then, set the `X-Auth-Scheme` header to `langsmith-api-key`.

If the PAT you pass is not tied to the owner of the agent, your request will be rejected with a 404 not found error.

If the agent you're trying to invoke is a workspace agent, and you're not the owner, you'll be able to preform all the same operations as you would in the UI (read-only).

## Example

To invoke the agent, you can copy the code below, and replace the `agent_id` and `api_url` with the correct values.

Alternatively, you can copy the same code shown below, but pre-populated with the proper agent ID and API URL, via the Agent Builder UI. To do this, navigate to the agent you want to invoke, visit the editor page, then click on the <Icon icon="gear" /> settings icon in the top right corner, and click `View code snippets`. You'll still need to manually set your `LANGGRAPH_API_KEY` environment variable.

<Tabs>
  <Tab title="Python">
    ```python theme={null}
    import os
    from dotenv import load_dotenv
    from langgraph_sdk.client import get_client

    load_dotenv()

    agent_id = "your-agent-id"

    # This must be a PAT API key tied to your user
    api_key = os.getenv("LANGGRAPH_API_KEY")
    api_url = "https://prod-agent-builder-5ccea139413e5ef289ab8e5d04688e11.us.langgraph.app"

    client = get_client(
        url=api_url,
        api_key=api_key,
        headers={
            "X-Auth-Scheme": "langsmith-api-key",
        },
    )

    async def get_assistant(agent_id: str):
        agent = await client.assistants.get(agent_id)
        print(agent)

    if __name__ == "__main__":
        import asyncio
        asyncio.run(get_assistant(agent_id))
    ```
  </Tab>

  <Tab title="TypeScript">
    ```ts theme={null}
    import "dotenv/config";
    import { Client } from "@langchain/langgraph-sdk";

    const agentId = "your-agent-id";

    // This must be a PAT API key tied to your user
    const apiKey = process.env.LANGGRAPH_API_KEY;
    const apiUrl = "https://prod-agent-builder-5ccea139413e5ef289ab8e5d04688e11.us.langgraph.app";

    const client = new Client({
      apiUrl,
      apiKey,
      defaultHeaders: {
        "X-Auth-Scheme": "langsmith-api-key",
      },
    });

    async function main(agentId: string) {
      const agent = await client.assistants.get(agentId);
      console.log(agent);
    }

    main(agentId).catch(console.error);
    ```
  </Tab>
</Tabs>

<Callout icon="key" color="#FEF3C7" iconType="regular">
  Use a PAT (Personal Access Token) API key tied to your user account. Set the `X-Auth-Scheme` header to `langsmith-api-key` for authentication. If you implemented custom authentication, pass your user's token in headers so the agent can use user‑scoped tools. See "Add custom authentication".
</Callout>

***

<Callout icon="pen-to-square" iconType="regular">
  [Edit the source of this page on GitHub.](https://github.com/langchain-ai/docs/edit/main/src/langsmith/agent-builder-code.mdx)
</Callout>

<Tip icon="terminal" iconType="regular">
  [Connect these docs programmatically](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
</Tip>