Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -1,10 +1,60 @@
|
|
| 1 |
---
|
| 2 |
title: Open Computer Use Agent
|
| 3 |
-
emoji:
|
| 4 |
-
colorFrom:
|
| 5 |
-
colorTo:
|
| 6 |
sdk: docker
|
|
|
|
| 7 |
pinned: false
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
title: Open Computer Use Agent
|
| 3 |
+
emoji: π₯οΈ
|
| 4 |
+
colorFrom: blue
|
| 5 |
+
colorTo: purple
|
| 6 |
sdk: docker
|
| 7 |
+
app_port: 7860
|
| 8 |
pinned: false
|
| 9 |
+
license: mit
|
| 10 |
---
|
| 11 |
|
| 12 |
+
# Open Computer Use Agent
|
| 13 |
+
|
| 14 |
+
An open-source alternative to OpenAI's Operator and Anthropic's Computer Use.
|
| 15 |
+
|
| 16 |
+
## Features
|
| 17 |
+
|
| 18 |
+
- π₯οΈ Full Linux desktop (Xfce) running in the browser
|
| 19 |
+
- π±οΈ Mouse control (click, double-click, right-click)
|
| 20 |
+
- β¨οΈ Keyboard input (typing, key combinations)
|
| 21 |
+
- π· Real-time screenshots
|
| 22 |
+
- π Firefox ESR browser included
|
| 23 |
+
|
| 24 |
+
## How It Works
|
| 25 |
+
|
| 26 |
+
This Space runs a virtual X11 desktop using:
|
| 27 |
+
- **Xvfb**: Virtual framebuffer for headless display
|
| 28 |
+
- **Xfce4**: Lightweight desktop environment
|
| 29 |
+
- **xdotool**: Mouse and keyboard automation
|
| 30 |
+
- **Gradio**: Web UI for control
|
| 31 |
+
|
| 32 |
+
## Usage
|
| 33 |
+
|
| 34 |
+
1. Click "Take Screenshot" to see the current desktop
|
| 35 |
+
2. Use the action controls to interact:
|
| 36 |
+
- Enter X,Y coordinates and click
|
| 37 |
+
- Type text
|
| 38 |
+
- Press keyboard shortcuts
|
| 39 |
+
- Scroll up/down
|
| 40 |
+
|
| 41 |
+
## Architecture
|
| 42 |
+
|
| 43 |
+
```
|
| 44 |
+
βββββββββββββββββββββββββββββββββββ
|
| 45 |
+
β HuggingFace Spaces Container β
|
| 46 |
+
β βββββββββββββ ββββββββββββββ β
|
| 47 |
+
β β Xvfb ββββ Xfce4 β β
|
| 48 |
+
β β :99 β β Desktop β β
|
| 49 |
+
β βββββββ¬ββββββ ββββββββββββββ β
|
| 50 |
+
β β β
|
| 51 |
+
β βββββββΌββββββ ββββββββββββββ β
|
| 52 |
+
β β xdotool ββββ Gradio β β
|
| 53 |
+
β β control β β UI :7860 β β
|
| 54 |
+
β βββββββββββββ ββββββββββββββ β
|
| 55 |
+
βββββββββββββββββββββββββββββββββββ
|
| 56 |
+
```
|
| 57 |
+
|
| 58 |
+
## License
|
| 59 |
+
|
| 60 |
+
MIT
|