🌐
Agent Browser
Browser Developer ToolsInstall Command
npx clawhub@latest install headless-browser
Installation Guide
1
Check Environment
Make sure Node.js 22+ and OpenClaw are installed. Run openclaw --version in your terminal to verify.
2
Run Installation
Run the install command above in your terminal. ClawHub will automatically download and install Agent Browser to the ~/.openclaw/skills/ directory.
3
Verify Installation
Run openclaw skills list to check your installed skills and confirm Agent Browser appears in the list.
4
Configure (Optional)
Follow the configuration instructions in the description below to add skill settings to ~/.config/openclaw/openclaw.json5.
Manual Installation: Copy the Skill folder to
~/.openclaw/skills/ or the skills/ directory in your project root. Make sure the folder contains a SKILL.md file.
Web Automation
Data Scraping
Screenshot Capture
Detailed Description
Agent Browser provides headless browser automation capabilities, letting OpenClaw operate a browser like a real person — clicking buttons, filling forms, scrolling pages, and extracting data.
Core Features
- Web Control: Simulate mouse clicks, keyboard input, page scrolling, and other user operations
- Data Scraping: Extract structured data from dynamically rendered web pages, supporting JavaScript-rendered pages
- Screenshots & PDF: Take screenshots or generate PDFs of web pages for archiving and reporting
- Cookie Management: Manage browser sessions and cookies, supporting authenticated operations
Configuration
{
skills: {
"headless-browser": {
browser: "chromium", // chromium, firefox
headless: true,
viewport: { width: 1280, height: 720 },
timeout: 30000, // Page load timeout (ms)
proxy: null
}
}
}
Use Cases
- Automate filling web forms and submission processes
- Scrape data from websites requiring JavaScript rendering
- End-to-end automated testing of website functionality
- Periodically screenshot web pages to monitor page changes