agent-browser

Overview

Automate browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

Key Features

• Navigate to URLs and interact with web pages
• Fill forms and input fields
• Take screenshots and save as images or PDFs
• Extract information from web pages
• Record video demos

How It Works

1. Navigate to a URL using agent-browser open <url>
2. Take a snapshot of the page using agent-browser snapshot -i to get interactive elements with refs
3. Interact with elements using refs from the snapshot
4. Re-snapshot after navigation or significant DOM changes

Use Cases

• Web testing and automation
• Form filling and data extraction
• Screenshot and PDF generation
• Video recording and demo creation