Skip to content
← All connectors
Developer

LangSmith

Use LangSmith with AI apps and agents through Vercel Connect. Follow a complete setup guide for secure runtime access.

Create Connector

  1. Install the skill

    $ npx skills add vercel/vercel-plugin --skill vercel-connect

  2. Connect to LangSmith

    Via CLIVercel Dashboard(opens in new tab)
    $ vercel connect create langsmith --name acme-langsmith

  3. Use its data in agents(opens in new tab) and apps(opens in new tab)

    import { getToken } from '@vercel/connect';
    

    const userId = 'user_123';
    

    const token = await getToken('langsmith/acme-langsmith', {
      subject: { type: 'user', id: userId },
    });

Use LangSmith in apps and agents

Inspect LLM traces, prompts, datasets, and evaluations.

Read the LangSmith developer docs(opens in new tab)

Why use Vercel Connect with LangSmith?

  • Credentials on demand

    Request LangSmith credentials only when your application or agent needs them instead of copying secrets into application code.

  • Access for the right subject

    Request user-authorized LangSmith access so actions follow the identity and permissions of the person using your application.

  • Centralized credential management

    Manage LangSmith credentials in one place and retrieve them through a consistent runtime API.

  • Vercel-native controls

    Bind connections to the projects and environments that need them while Vercel OIDC authenticates each runtime request.

Use LangSmith with your stack

Follow a complete setup for the Connect SDK or a supported agent framework.

Add LangSmith to an existing Vercel application with the Connect SDK.

  1. Install the Connect SDK

    npm install @vercel/connect

  2. Create the LangSmith connector

    Run these commands from the project that will use the connection.

    vercel link
    vercel connect create langsmith --name acme-langsmith
    vercel env pull

  3. Request LangSmith credentials

    app/api/route.ts
    import { getToken } from '@vercel/connect';
    

    const userId = 'user_123';
    

    const token = await getToken('langsmith/acme-langsmith', {
      subject: { type: 'user', id: userId },
    });

More connectors like LangSmith

Browse all connectors