I loved the idea of Cluely, an AI that reads your meetings and screen to give instant answers, but it’s pricey. So I built my own version in Python using OCR (Tesseract) to capture screen text, Whisper for audio transcription, and Google’s Gemini API (with BYO key) for responses, all shown in a translucent always-on-top overlay, invisible to others
-
Updated
Sep 2, 2025 - Python