agent-browser - Browser automation CLI for AI agents.
Automates browser interactions including web navigation, form filling, element clicking, page screenshots, and data extraction.
Tags
Updated: 2026-09-18Capabilities
Typical Inputs
Typical Outputs
What this skill does
- Navigate to target web pages
- Capture interactive element snapshots
- Click interactive web elements
- Fill form input fields
- Extract text from web pages
- Take web page screenshots
- Export web pages to PDF
- Save and load session state
- Manage parallel browser sessions
- Automate iOS Simulator Safari
Inputs
- Target website URLs
- Element references and locators
- Form input values
- Saved state JSON files
- Local file paths
- iOS simulator device names
Outputs
- Interactive element snapshots
- Extracted text and metadata
- Page screenshot images
- Exported PDF files
- Session video recordings
- Saved browser state files
Requirements
- agent-browser CLI tool
- Bash execution environment
- macOS with Xcode for iOS
- Appium with xcuitest driver