agent-browser - Browser Automation CLI for AI Agents
Automates browser interactions including navigation, form filling, clicking buttons, and data extraction
Tags
Updated: 2026-02-11Capabilities
Typical Inputs
Typical Outputs
What this skill does
- open website pages
- fill form fields
- click buttons and links
- take webpage screenshots
- extract text data
- wait for page loading
- save webpage as PDF
- manage browser session state
- test in iOS simulator
Inputs
- target website URLs
- browser session configuration
- iOS device information
- form data inputs
- authentication credentials
Outputs
- webpage screenshots
- PDF documents
- extracted text data
- browser session state files
- recorded video files
Requirements
- Bash environment
- macOS system (for iOS simulator)
- Xcode (for iOS testing)
- Appium driver (mobile automation)