metadata
title: Open Computer Use Agent
emoji: 🖥️
colorFrom: blue
colorTo: purple
sdk: docker
app_port: 7860
pinned: false
license: mit
Open Computer Use Agent
An open-source alternative to OpenAI's Operator and Anthropic's Computer Use.
Features
- 🖥️ Full Linux desktop (Xfce) running in the browser
- 🖱️ Mouse control (click, double-click, right-click)
- ⌨️ Keyboard input (typing, key combinations)
- 📷 Real-time screenshots
- 🌐 Firefox ESR browser included
How It Works
This Space runs a virtual X11 desktop using:
- Xvfb: Virtual framebuffer for headless display
- Xfce4: Lightweight desktop environment
- xdotool: Mouse and keyboard automation
- Gradio: Web UI for control
Usage
- Click "Take Screenshot" to see the current desktop
- Use the action controls to interact:
- Enter X,Y coordinates and click
- Type text
- Press keyboard shortcuts
- Scroll up/down
Architecture
┌─────────────────────────────────┐
│ HuggingFace Spaces Container │
│ ┌───────────┐ ┌────────────┐ │
│ │ Xvfb │◄─│ Xfce4 │ │
│ │ :99 │ │ Desktop │ │
│ └─────┬─────┘ └────────────┘ │
│ │ │
│ ┌─────▼─────┐ ┌────────────┐ │
│ │ xdotool │◄─│ Gradio │ │
│ │ control │ │ UI :7860 │ │
│ └───────────┘ └────────────┘ │
└─────────────────────────────────┘
License
MIT