eyadsibai agent-browser: CLI Browser Automation
Vercel's headless browser automation CLI designed for AI agents. Uses ref-based selection (@e1, @e2) from accessibility snapshots.
Setup
# Check installation
command -v agent-browser >/dev/null 2>&1 && echo "Installed" || echo "NOT INSTALLED"
# Install if needed
npm install -g agent-browser
agent-browser install # Downloads Chromium
Core Workflow
The snapshot + ref pattern is optimal for LLMs:
- Navigate to URL
- Snapshot to get interactive elements with refs
- Interact using refs (@e1, @e2, etc.)
- Re-snapshot after navigation or DOM changes
agent-browser open https://example.com
agent-browser snapshot -i # Get refs
agent-browser click @e1 # Use ref
agent-browser fill @e2 "text"
agent-browser snapshot -i # Re-snapshot
Key Commands
Navigation
agent-browser open <url> # Navigate to URL
agent-browser back # Go back
agent-browser forward # Go forward
agent-browser reload # Reload page
agent-browser close # Close browser
Snapshots (Essential for AI)
agent-browser snapshot # Full accessibility tree
agent-browser snapshot -i # Interactive elements only (recommended)
agent-browser snapshot -i --json # JSON output for parsing
agent-browser snapshot -c # Compact (remove empty)
agent-browser snapshot -d 3 # Limit depth
Interactions
agent-browser click @e1 # Click element
agent-browser dblclick @e1 # Double-click
agent-browser fill @e1 "text" # Clear and fill input
agent-browser type @e1 "text" # Type without clearing
agent-browser press Enter # Press key
agent-browser hover @e1 # Hover element
agent-browser check @e1 # Check checkbox
agent-browser uncheck @e1 # Uncheck
agent-browser select @e1 "option" # Select dropdown
agent-browser scroll down 500 # Scroll
agent-browser scrollintoview @e1 # Scroll element into view
Get Information
agent-browser get text @e1 # Get element text
agent-browser get html @e1 # Get element HTML
agent-browser get value @e1 # Get input value
agent-browser get attr href @e1 # Get attribute
agent-browser get title # Get page title
agent-browser get url # Get current URL
Screenshots & PDFs
agent-browser screenshot # Viewport screenshot
agent-browser screenshot --full # Full page
agent-browser screenshot output.png # Save to file
agent-browser pdf output.pdf # Save as PDF
Wait
agent-browser wait @e1 # Wait for element
agent-browser wait 2000 # Wait milliseconds
agent-browser wait "text" # Wait for text
Examples
Login Flow
agent-browser open https://app.example.com/login
agent-browser snapshot -i
# Output: textbox "Email" [ref=e1], textbox "Password" [ref=e2], button "Sign in" [ref=e3]
agent-browser fill @e1 "user@example.com"
agent-browser fill @e2 "password123"
agent-browser click @e3
agent-browser wait 2000
agent-browser snapshot -i # Verify logged in
Form Filling
agent-browser open https://forms.example.com
agent-browser snapshot -i
agent-browser fill @e1 "John Doe"
agent-browser fill @e2 "john@example.com"
agent-browser select @e3 "United States"
agent-browser check @e4 # Agree to terms
agent-browser click @e5 # Submit
agent-browser screenshot confirmation.png
Debug Mode (Visible Browser)
agent-browser --headed open https://example.com
agent-browser --headed snapshot -i
agent-browser --headed click @e1
Sessions (Parallel Browsers)
agent-browser --session browser1 open https://site1.com
agent-browser --session browser2 open https://site2.com
agent-browser session list
JSON Output
agent-browser snapshot -i --json
Returns:
{
"success": true,
"data": {
"refs": {
"e1": {"name": "Submit", "role": "button"},
"e2": {"name": "Email", "role": "textbox"}
}
}
}
When to Use vs Alternatives
Use agent-browser when:
- Prefer Bash-based workflows
- Need quick one-off automation
- Want simpler CLI commands
Use Playwright MCP when:
- Need deep MCP tool integration
- Building complex automation pipelines
- Want tool-based responses