Agent Browser Integration
Agent Browser is a headless browser automation CLI for AI agents, built with a fast Rust CLI and Node.js fallback. By connecting agent-browser to Browserless, you get cloud-hosted browsers without managing Chrome infrastructure yourself, complete with stealth mode, residential proxies, and enterprise-grade reliability.
Prerequisites
- Node.js 18 or later
- agent-browser installed globally or as a project dependency
- Browserless API token (available in your account dashboard)
Step-by-Step Setup
1. Get your API token
Go to your Browserless Account Dashboard and copy your API token.
Then set your environment variable:
- .env file
- Command line
BROWSERLESS_API_KEY=your-api-token
export BROWSERLESS_API_KEY="your-api-token"
2. Install agent-browser
- Global (recommended)
- npx (no install)
- Project dependency
npm install -g agent-browser
npx agent-browser open https://example.com
npm install agent-browser
3. Connect to Browserless
Use the -p browserless flag to route all browser commands through Browserless:
export BROWSERLESS_API_KEY="your-api-token"
agent-browser -p browserless open https://example.com
Or use environment variables for CI/scripts:
export AGENT_BROWSER_PROVIDER=browserless
export BROWSERLESS_API_KEY="your-api-token"
agent-browser open https://example.com
When enabled, agent-browser connects to a Browserless cloud session instead of launching a local browser. All commands work identically.
4. Run browser automation
Use agent-browser's CLI commands with the Browserless-powered browser:
# Navigate and take a snapshot
agent-browser -p browserless open https://www.browserless.io
agent-browser snapshot
# Interact using refs from the snapshot
agent-browser click @e2
agent-browser fill @e3 "test@example.com"
# Get text content and screenshots
agent-browser get text @e1
agent-browser screenshot page.png
# Clean up
agent-browser close
Optional Configuration
Configure Browserless behavior via environment variables:
| Variable | Description | Default |
|---|---|---|
BROWSERLESS_API_URL | Base API URL (for custom regions or self-hosted) | https://production-sfo.browserless.io |
BROWSERLESS_BROWSER_TYPE | Type of browser to use (chromium or chrome) | chromium |
BROWSERLESS_TTL | Session TTL in milliseconds | 300000 |
BROWSERLESS_STEALTH | Enable stealth mode (true / false) | true |
Regional endpoints
Pick the region closest to you for lower latency:
| Region | BROWSERLESS_API_URL value |
|---|---|
| US West (San Francisco) | https://production-sfo.browserless.io |
| Europe (London) | https://production-lon.browserless.io |
| Europe (Amsterdam) | https://production-ams.browserless.io |
Usage with AI Agents
agent-browser is designed for AI coding assistants and autonomous agents. Add it to your agent's instructions:
Use agent-browser to browse the web. Run agent-browser --help for all commands.
Core workflow:
1. agent-browser -p browserless open <url>
2. agent-browser snapshot -i (get interactive elements with refs @e1, @e2)
3. agent-browser click @e1 / fill @e2 "text" (interact using refs)
4. Re-snapshot after page changes
For richer context in AI coding assistants (Claude Code, Cursor, Codex, etc.):
npx skills add vercel-labs/agent-browser
Why use Browserless with agent-browser
- Stealth mode: bypass bot detection with stealth enabled by default
- Residential proxies: route traffic through real residential IPs to avoid blocks
- Global regions: choose from US West (San Francisco), Europe (London), or Europe (Amsterdam) endpoints for lower latency
- No infrastructure: skip managing Chrome installations, updates, or scaling
- Parallel sessions: run multiple browser sessions simultaneously
- Enterprise reliability: 99.9% uptime SLA with automatic failover