Managing speaking order fairly and quickly in crowded halls is a much more difficult problem than it seems. Who raised their hand? Whose request to speak was overlooked? How can the moderator manage this order in an organized manner? I want to share my open-source project that I developed based on this problem: RaiseTrack AI RaiseTrack AI is an AI-powered system that aims to anonymously identify participants who raise their hands to request the right to speak in conference halls, city councils, classrooms, and large meeting areas, and to create a live speaking order for the moderator. The most important principle in the project was Privacy-by-Design. The system: Does not perform facial recognition. Does not track personal identity. Does not record images, videos, or base64 data. Works only with anonymous zone, coordinate, and speaking order metadata. Technologies I used: Python, FastAPI, OpenCV, MediaPipe, Pydantic, Vanilla JavaScript, Canvas Overlay, WebSocket/Polling fallback. The project is currently an open-source demo MVP at the release candidate level, having passed over 1100 tests. GitHub: https://lnkd.in/dv3Wb9NY I would be happy to hear your feedback and suggestions.