#agent-browser #cdp #screenshot #browser-automation

Browser Agent (CDP)

Self-contained browser automation plugin for OpenClaw. Install once, automate websites via CDP — navigate, click, fill forms, screenshot, scrape data. Powered by agent-browser.

Frrrrrrrrank@frrrrrrrrank

Install

openclaw plugins install clawhub:openclaw-browser-agent

Browser Agent (CDP) — OpenClaw Plugin

AI-powered browser automation for OpenClaw via Chrome DevTools Protocol.

What it does

Gives your OpenClaw agent the ability to control a real browser:

Navigate to URLs
Click elements, fill forms, select dropdowns
Take screenshots
Extract text, HTML, and page data
Execute JavaScript
Batch multiple commands

Install

bash

openclaw plugins install @openclaw-plugins/browser-agent

Setup

Install agent-browser:

bash

npm install -g agent-browser
agent-browser install

To control an existing Chrome, launch it with CDP enabled:
bash
```
chrome --remote-debugging-port=9222
```
Connect:
bash
```
agent-browser connect 9222
```

Tools Provided

Tool	Description
`browser_open`	Navigate to a URL
`browser_snapshot`	Get page accessibility tree with refs
`browser_click`	Click element by ref
`browser_fill`	Fill form field
`browser_screenshot`	Capture screenshot
`browser_get`	Extract page data
`browser_eval`	Run JavaScript (optional)
`browser_batch`	Multi-command execution