Runtime
Use Runtime with AI apps and agents through Vercel Connect. Follow a complete setup guide for secure runtime access.
Install the skill
$ npx skills add vercel/vercel-plugin --skill vercel-connectConnect to
Runtime$ vercel connect create runtime --name acme-runtimeUse 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('runtime/acme-runtime', {subject: { type: 'user', id: userId },});
Use Runtime in apps and agents
Run code in Linux sandboxes for AI agents.
Read the Runtime developer docs(opens in new tab)Why use Vercel Connect with Runtime?
Credentials on demand
Request Runtime credentials only when your application or agent needs them instead of copying secrets into application code.
Access for the right subject
Request user-authorized Runtime access so actions follow the identity and permissions of the person using your application.
Centralized credential management
Manage Runtime 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 Runtime with your stack
Follow a complete setup for the Connect SDK or a supported agent framework.
Add Runtime to an existing Vercel application with the Connect SDK.
Install the Connect SDK
npm install @vercel/connectCreate the Runtime connector
Run these commands from the project that will use the connection.
vercel linkvercel connect create runtime --name acme-runtimevercel env pullRequest Runtime credentials
app/api/route.tsimport { getToken } from '@vercel/connect';const userId = 'user_123';const token = await getToken('runtime/acme-runtime', {subject: { type: 'user', id: userId },});