Weights & Biases
Use Weights & Biases 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
Use its data in agents(opens in new tab) and apps(opens in new tab)
import { getToken } from '@vercel/connect';const token = await getToken('weights-and-biases/acme-weights-and-biases');
Use Weights & Biases in apps and agents
Explore machine learning projects, runs, artifacts, and reports.
Why use Vercel Connect with Weights & Biases?
Credentials on demand
Request Weights & Biases credentials only when your application or agent needs them instead of copying secrets into application code.
Access for the right subject
Keep app-scoped Weights & Biases access behind a reusable connector controlled by your team.
Centralized credential management
Manage Weights & Biases 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 Weights & Biases with your stack
Follow a complete setup for the Connect SDK or a supported agent framework.
Add Weights & Biases to an existing Vercel application with the Connect SDK.
Install the Connect SDK
npm install @vercel/connectCreate the Weights & Biases connector
Run these commands from the project that will use the connection.
vercel linkvercel connect create weights-and-biases --name acme-weights-and-biasesvercel env pullRequest Weights & Biases credentials
app/api/route.tsimport { getToken } from '@vercel/connect';const token = await getToken('weights-and-biases/acme-weights-and-biases');
