Commands
Complete reference for all AGENT BROWSER commands. All commands operate on the active browser session unless otherwise noted.
Core navigation
Navigation & interaction
agent-browser open # Launch browser (no navigation)
agent-browser open <url> # Launch + navigate to URL
agent-browser read [url] # Fetch agent-readable text
agent-browser click <sel> # Click element
agent-browser dblclick <sel> # Double-click element
agent-browser focus <sel> # Focus element
agent-browser type <sel> <text> # Type into element
agent-browser fill <sel> <text> # Clear and fill
agent-browser press <key> # Press key (Enter, Tab, Control+a)
agent-browser hover <sel> # Hover over element
agent-browser select <sel> <value> # Select dropdown option
agent-browser check <sel> # Check checkbox/radio
agent-browser uncheck <sel> # Uncheck checkbox
agent-browser scroll <sel> <dir> # Scroll element (up/down/left/right)
agent-browser drag <src> <dest> # Drag and dropCapturing state
Capture & control
agent-browser screenshot [path] # Screenshot viewport (PNG)
agent-browser screenshot --full # Full-page screenshot
agent-browser pdf <path> # Save page as PDF
agent-browser snapshot # Accessibility tree with refs
agent-browser snapshot -i # Interactive compact snapshot
agent-browser eval <js> # Run JavaScript
agent-browser connect <port|url> # Connect to browser via CDP
agent-browser stream enable # Start runtime WebSocket streaming
agent-browser stream status # Show streaming state
agent-browser stream disable # Stop streaming
agent-browser close # Close browser
agent-browser close --all # Close all active sessions
agent-browser mcp # Start MCP stdio serverGet info
Get information
agent-browser get text <sel> # Get text content
agent-browser get html <sel> # Get innerHTML
agent-browser get value <sel> # Get input value
agent-browser get attr <sel> <attr> # Get attribute
agent-browser get title # Get page title
agent-browser get url # Get current URL
agent-browser get cdp-url # Get CDP WebSocket URL
agent-browser get count <sel> # Count matching elements
agent-browser get box <sel> # Get bounding box
agent-browser get styles <sel> # Get computed stylesRead agent-friendly text
Read command options
agent-browser read
agent-browser read https://example.com/article
agent-browser read https://example.com/article --filter overview
agent-browser read https://example.com/article --outline
agent-browser read https://docs.example.com --llms index --filter auth
agent-browser read https://docs.example.com --llms full --filter auth
agent-browser read example.com/article --require-md
agent-browser read https://example.com/article --jsonCheck state
State checks
agent-browser is visible <sel> # Check if visible
agent-browser is enabled <sel> # Check if enabled
agent-browser is checked <sel> # Check if checkedFind elements (semantic locators)
Semantic element finders
agent-browser find role <role> <action> [value] # By ARIA role
agent-browser find text <text> <action> # By text content
agent-browser find label <label> <action> [value] # By label
agent-browser find placeholder <ph> <action> [value] # By placeholder
agent-browser find alt <text> <action> # By alt text
agent-browser find title <text> <action> # By title attr
agent-browser find testid <id> <action> [value] # By data-testid
agent-browser find first <sel> <action> [value] # First matchNetwork
Network control
agent-browser network block <pattern> # Block URL pattern
agent-browser network unblock <pattern> # Unblock URL pattern
agent-browser network unblock --all # Remove all blocks
agent-browser network throttle slow-3g # Throttle network
agent-browser network throttle --reset # Remove throttleStorage
Storage commands
agent-browser storage get local <key> # Get localStorage value
agent-browser storage set local <key> <val> # Set localStorage value
agent-browser storage remove local <key> # Remove localStorage key
agent-browser storage clear local # Clear all localStorage
agent-browser storage get session <key> # Same for sessionStorage
agent-browser storage get cookie <name> # Get cookie value
agent-browser storage set cookie <n> <v> # Set cookie
agent-browser storage remove cookie <name> # Delete cookieTabs
Tab management
agent-browser tab list # List open tabs
agent-browser tab new [url] # Open new tab
agent-browser tab switch <index|title> # Switch active tab
agent-browser tab close [index] # Close a tabSelectors
All commands accept the following selector formats:
| Format | Example | Notes |
|---|---|---|
| Ref | @e1 | From snapshot. Preferred for agents. |
| CSS selector | #submit | Standard CSS. Works with any valid selector. |
| XPath | //button[@type='submit'] | Full XPath support. |
| Text | text=Submit | Matches by visible text content. |
Next: Configuration