on-device inference

wavecat is a fully local personal agent that watches your screen and runs entirely on-device. The page explains its privacy focus, hardware requirements, local model setup, and supported platforms.

QVAC SDK 0.12.0 adds TurboQuant, a KV-cache quantization feature for local LLM inference that claims up to 5x more context on-device with no retraining or code changes.

An open-source project for running a small LLM and limited agent workflows on ESP32-P4 hardware, with model details, architecture notes, examples, and setup instructions.