Matt Mireles

gemma-tuner-multimodal. Fine-tune Gemma 4 and 3n with audio, images and text on Apple Silicon, using PyTorch and Metal Performance Shaders.

Flatty. transform an entire GitHub repo into a simple text file so that you can upload it to an LLM (Claude, ChatGPT, etc.)

kokoro-coreml. PyTorch → CoreML conversion pipeline for Kokoro TTS. Unlocks fast on-device text-to-speech on Apple Neural Engine.

magenta-realtime-2-iphone. Google's MRT2 → Core ML, full Apple Neural Engine execution, zero GPU. Runs locally on iPhone without burning your hand.

Hyperchat. All Your AIs. All At Once. The ultimate  macOS desktop app for multi-GPT chat.

Gdump. Hit Gemini API's secret 20GB file limit? Dump them all and get back to work.

mic-to-mp3. Record audio in the browser. Get an MP3 you can feed to an LLM.