An AI with Twitch integration, designed to interact and respond in real time. The system uses Ollama for its language model, GPT-SoVITS for custom voice synthesis, and faster-whisper for speech recognition. Most of the system runs on my own hardware, with the AI tuned to react to what's actually happening rather than making up information about the current state.

A Tkinter control panel that brings together microphone boost, speech-to-text, and push-to-talk controls for the desktop voice setup. When using VRChat, only the speech-to-text system is used, sending the recognized input through OSC. This lets me manage the voice setup and interact with VRChat without needing to constantly switch back to the keyboard.

Real-time phone-to-PC camera streaming over HTTPS and WebSockets. Turning my phone into a proper wireless webcam without any third-party apps.

Electron app using MediaPipe pose landmarking to drive VRChat avatars over OSC — camera-based FBT, no dedicated trackers needed.

Python SteamVR overlay for dimming the Meta Quest 2 display from inside VR using the controllers. Small QoL thing I use constantly.