huangjunsen0406/py-xiaozhi ? reverse-engineered prompt

Build me a cross platform AI voice assistant app in Python that feels like a real product, not just a demo.

I want it to run on Windows, macOS, and Linux, with a simple desktop interface plus a command line mode for headless use. It should handle live voice conversations, support wake word listening, and be able to see images from a camera for basic visual understanding. I also want it to connect to smart devices and hardware through MQTT or WebSocket, so it can control lights, sensors, GPIO, and simple robot style actions on things like Raspberry Pi or other edge boards.

Please include a modular tool system so it can call helper tools like music, weather, screenshots, volume, camera, and app control. Make it easy to plug in new tools later, and keep the code clean and async. If you need to check current docs or APIs for anything, look them up online. I want the result to be usable, easy to start, and polished enough that someone could actually run it on a small device.