I'm building a life OS that runs a 4B parameter AI model on your phone — zero cloud, zero subscription, zero data leaving your device
LifeOS is a React Native productivity app where every intelligent feature — scheduling, notifications, task extraction, weekly reviews — runs on a locally-quantized Gemma 4 model. No OpenAI, no Anthropic, no API bill. Here's every technical decision that makes this possible, and the constraint that forces all of them.