ferranpons/Llamatik

Based on the README, here's the technical summary: Wraps **llama.cpp**, **whisper.cpp**, and **stable-diffusion.cpp** behind a unified Kotlin API with **schema-constrained JSON generation** and streaming support for LLMs. Native C++ integration via Kotlin/Native (iOS frameworks) and JNI (Android/Desktop) enables true offline inference without Python dependencies. Supports hybrid operation—seamlessly switch between on-device and HTTP-based remote inference with identical API calls, backed by an optional `llamatik-backend` server.