Loading repository data…
Loading repository data…
nwx77 / repository
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
A transparent discovery signal based on current public GitHub metadata.
This score does not audit code, security, maintainers, documentation quality, or suitability. Verify the repository and its current documentation before adoption.
a local-first, undetectable AI desktop assistant that listens to meetings and on-screen content, then provides real-time answers using Google's Gemini API. Built with Python and designed to be invisible to others in video calls.
The assistant appears as a translucent overlay in the top-right corner of your screen, providing instant AI-powered responses based on your current context.
git clone <repository-url>
cd hintly
pip install -r requirements.txt
C:\Program Files\Tesseract-OCRWindows:
set GEMINI_API_KEY=your_api_key_here
Linux/Mac:
export GEMINI_API_KEY=your_api_key_here
python cluely_assistant.py
Ctrl + Alt + C (default)Ctrl + Alt + V (optional)− button to hide× button to exitEdit config.py to customize:
┌─────────────────┐ ┌─────────────────┐ ┌─────────────────┐
│ Screen Capture│ │ Audio Capture │ │ Gemini API │
│ (OCR) │ │ (Whisper) │ │ (AI) │
└─────────────────┘ └─────────────────┘ └─────────────────┘
│ │ │
└───────────────────────┼───────────────────────┘
│
┌─────────────────┐
│ Main Assistant │
│ (Orchestrator)│
└─────────────────┘
│
┌─────────────────┐
│ Overlay UI │
│ (PyQt5) │
└─────────────────┘
"GEMINI_API_KEY not set"
OCR not working
Audio not capturing
Overlay not appearing
Ctrl + Alt + CCheck cluely_assistant.log for detailed error information.
hintly/
├── cluely_assistant.py # Main application entry point
├── config.py # Configuration settings
├── screen_capture.py # OCR and screen capture
├── audio_capture.py # Audio recording and transcription
├── gemini_client.py # Google Gemini API integration
├── overlay_ui.py # PyQt5 overlay interface
├── hotkey_manager.py # Global hotkey handling
├── requirements.txt # Python dependencies
└── README.md # This file
This project is open source. Please respect the privacy and security guidelines when using or modifying this software.
For issues and questions:
Note: This is a local-first implementation designed for personal use. Always respect privacy and security best practices when using AI assistants.