Show HN: AI gaming copilot that uses a phone camera instead of screen capture (github.com)

A newly released project called Aegis introduces an innovative AI gaming copilot that analyzes gameplay using a separate device like a smartphone or an HDMI capture card, rather than traditional screen capture methods. This air-gapped solution operates without intrusive code injections or kernel access, making it undetectable by anti-cheat software. The system captures game frames via a WebSocket connection or video capture, processes them with contrast enhancement, and sends the data to the Claude Opus 4.6 AI for real-time analysis. It provides structured feedback on game situations — for example, health status, threats, and strategic recommendations — displayed through a web interface and optionally vocalized through text-to-speech. This development is significant for the AI/ML community as it sets a new precedent for game assistance tools that respect user privacy and game integrity while still delivering intelligent support. Developers can easily integrate and customize the system using Python, enhancing accessibility for users as it allows for a wide range of configurations. With its reliance on advanced AI capabilities and a focus on non-intrusive analysis, Aegis could pave the way for a new generation of game assistants that enhance gameplay while adhering to the stringent requirements of fair play.