Vercel Sandbox

The vercel-sandbox skill enables developers to run agent-browser with headless Chrome inside ephemeral Vercel Sandbox microVMs for browser automation tasks. It solves the problem of executing browser automation in Vercel-deployed applications (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.) without binary size constraints or infrastructure setup, providing on-demand Linux VMs that spin up, execute commands, and shut down automatically. The skill supports both snapshot-based rapid startup and standard initialization with system dependencies and agent-browser installation.

skills.sh installs: 11.3K
GitHub stars: 29.3K

View on GitHub

Install

$ npx -y skills add vercel-labs/agent-browser --skill vercel-sandbox --agent claude-code

Installs into .claude/skills of the current project.

Files

Browser Automation with Vercel Sandbox

Run agent-browser + headless Chrome inside ephemeral Vercel Sandbox microVMs. A Linux VM spins up on demand, executes browser commands, and shuts down. Works with any Vercel-deployed framework (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.).

Dependencies

pnpm add @agent-browser/sandbox @vercel/sandbox

The sandbox VM needs system dependencies for Chromium plus agent-browser itself. The @agent-browser/sandbox helpers install them by default for fresh sandboxes and use sandbox snapshots (below) for sub-second startup. Pass installSystemDependencies: false only when the sandbox image already provides Chromium's required libraries.

Core Pattern

import {
  createAgentBrowserSnapshot,
  runAgentBrowserCommand,
  withAgentBrowserSandbox,
  type VercelSandboxSession,
} from "@agent-browser/sandbox/vercel";

async function withBrowser<T>(
  fn: (sandbox: VercelSandboxSession) => Promise<T>,
): Promise<T> {
  return withAgentBrowserSandbox(fn);
}