agent-browser - Browser Automation CLI for AI Agents
A CLI tool for AI agents to automate browser navigation, DOM element interaction, content extraction, and session management.
Tags
Updated: 2026-09-17Capabilities
Typical Inputs
Typical Outputs
What this skill does
- Navigate web pages and URLs
- Capture interactive DOM element snapshots
- Interact with page elements
- Extract text and page title
- Save and load authentication states
- Capture screenshots and PDF files
- Manage parallel browser sessions
- Automate Mobile Safari on iOS
Inputs
- Target URLs
- Snapshot element references or locators
- Authentication credentials
- Saved state files
- iOS device names or UDIDs
Outputs
- DOM element snapshot references
- Extracted text content
- Session state files
- Screenshot image files
- PDF document files
- Video recordings
Requirements
- macOS with Xcode for iOS Simulator support
- Appium with xcuitest driver for iOS Simulator support