Skip to main content

Solution

Shadow Automator is a local desktop automation agent. You describe what you want in natural language via a Ctrl+Space Spotlight bar. The system:

  1. Captures your screen (via mss) and redacts PII (credit cards, SSNs, emails) offline with OpenCV + regex
  2. Sends the sanitised screenshot to a locally-hosted Qwen2.5-VL-3B vision model
  3. Receives exact [x1, y1, x2, y2] bounding-box coordinates for the target element
  4. Projects glowing AR bounding boxes on-screen via a transparent overlay
  5. Clicks with human-like mouse smoothing via PyAutoGUI
  6. Self-heals if no UI state change is detected — automatically re-crops and re-grounds
  7. Logs every task to SQLite and displays live ROI savings (cloud cost + human hours avoided)

Built with

python

AI tools

Coded withClaude CodeAntigravityGemini 3.8 FlashGrok 4.7

Prize Categories Entered

  • DigitalOcean

    Best Open-Source AI Project

    Submitted