A specialized toolset for running headful or headless Chrome on Linux servers using XVFB to enable seamless AI-driven browser automation.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install xvfb-chrome
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 xvfb-chrome 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 XVFB Chrome Automation?
The XVFB Chrome skill provides a comprehensive framework for running the Google Chrome browser on headless Linux environments. By utilizing the X Virtual Frame Buffer (XVFB), developers can simulate a display environment, allowing headful browser features to function on servers without physical monitors. This is particularly valuable for users of Openclaw Skills who need to integrate AI agents with real-time web browsing, complex UI interactions, and visual debugging.
This setup bridges the gap between traditional headless browsing and full graphical interaction. It enables the use of the Chrome DevTools Protocol (CDP) through a dedicated remote debugging port, making it a cornerstone for modern automation workflows. Whether you are performing high-fidelity web scraping or automated UI testing, this skill ensures your Openclaw Skills have the graphical backend they require.
XVFB Chrome Automation Use Cases
- Executing automated web scraping and data extraction on cloud-based Linux servers.
- Generating high-resolution screenshots and visual snapshots of dynamic web pages.
- Powering AI-driven browser interactions via the chrome-devtools MCP server.
- Debugging complex JavaScript-heavy websites in a headful environment without a local GUI.
- Running automated end-to-end tests that require a real browser display buffer.
How XVFB Chrome Automation Works
- Initialize the XVFB virtual display to create a simulated graphical environment on the server.
- Launch Google Chrome using specific CLI flags such as --no-sandbox and --disable-gpu to ensure compatibility with server environments.
- Enable the remote debugging port (typically 9222) to allow external tools and AI agents to communicate with the browser.
- Connect an MCP (Model Context Protocol) server to the browser instance to translate AI instructions into browser actions.
- Execute automation tasks like navigation, element clicking, and script evaluation through the established debugging bridge.
- Manage the browser lifecycle by monitoring processes and cleaning up virtual display buffers as needed within your Openclaw Skills workflow.
XVFB Chrome Automation Setup
Prerequisites
Ensure your Linux server has Chrome and XVFB installed.
Basic Launch
To start Chrome in headful mode with a virtual display for Openclaw Skills integration, use the following command:
xvfb-run -a google-chrome --no-sandbox --disable-gpu --remote-debugging-port=9222 --user-data-dir=/tmp/chrome-profile &
Connection Verification
Check if the browser is ready to receive commands:
curl -s http://127.0.0.1:9222/json/version
XVFB Chrome Automation Data Schema & Taxonomy
The skill manages browser state and metadata through several key parameters and directories:
| Parameter | Description | Usage |
|---|---|---|
| --user-data-dir | Path to the browser profile, storing cookies and session data | Persistent sessions |
| --remote-debugging-port | The TCP port used for CDP and MCP communication | Default: 9222 |
| DISPLAY | Environmental variable mapping the browser to an XVFB instance | e.g., DISPLAY=:99 |
| Screen Resolution | Configuration for the virtual buffer size | e.g., 1280x720x24 |
Files generated typically include screenshots (PNG) and page snapshots (HTML/JSON) stored in specified output paths.
XVFB Chrome Automation Advanced Features
- Multi-resolution support allowing for 720p and 1080p virtual buffers to accommodate different layout requirements.
- Full integration with chrome-devtools MCP for advanced tool calling like
evaluate_scriptandlist_network_requests. - Automatic display allocation using the
xvfb-run -aflag to prevent port conflicts. - Process isolation using unique user data directories for concurrent Openclaw Skills sessions.
- Robust process management scripts for killing and restarting clean browser instances.
SKILL.md
Loading
Related Openclaw Skills
browsex
A browser-based CLI skill for interacting with X/Twitter through the OpenClaw agent, supporting both authenticated and read-only actions.
BrainRepo
A comprehensive personal knowledge repository that utilizes PARA and Zettelkasten methodologies to capture, organize, and retrieve information via AI agents.
AgoraHub
AgoraHub is an open agent registry providing over 14 verified AI tools for common developer tasks like data conversion, hashing, and formatting.
Firefly AI Integration
Retrieve meeting transcripts, summaries, and action items directly from fireflies.ai using GraphQL.
Crawl4ai
An advanced AI-powered web scraping framework designed to extract structured, clean data from complex websites and dynamic JavaScript-heavy environments.
Aionis Memory Policy Loop
A professional integration skill connecting OpenClaw to Aionis for advanced long-term memory, context-aware tool routing, and feedback-driven policy loops.
Featured*
