Home Tutorials Categories Skills About
ZH EN JA KO
🤖

Agent Browser

Browser Browser & Automation

Install Command

npx clawhub@latest install agent-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.
Playwright Form Filling Screenshots

Detailed Description

Agent Browser is OpenClaw's "eyes and hands," enabling the AI to operate a web browser just like a human to complete various web interaction tasks.

Core Features

  • Web Browsing: Open URLs, navigate, scroll, and wait for page loads
  • Element Interaction: Click buttons, fill forms, select dropdown options, upload files
  • Information Extraction: Get page text, read table data, extract specific element content
  • Screenshots: Capture screenshots of entire pages or specific areas
  • Multiple Tabs: Support opening and operating multiple tabs simultaneously
  • Cookie Management: Save and restore login states

Configuration

Requires Playwright dependencies to be installed.

{
  skills: {
    "agent-browser": {
      headless: true,
      viewport: { width: 1280, height: 720 },
      timeout: 30000,
      userAgent: "custom-ua-string"
    }
  }
}

After installation, also run npx playwright install chromium to install the browser engine.

Use Cases

  • Automatically fill out online forms and applications
  • Scrape dynamic webpage content that requires JavaScript rendering
  • Automate website functional testing
  • Capture webpage snapshots for reports or archiving

Notes

Browser automation consumes significant system resources. It is recommended to run in headless mode on the server side and set reasonable timeout values.

← Back to Skills List