annadata

A native Capacitor plugin that embeds llama.cpp directly into mobile apps, enabling offline AI inference with chat-first API design. Complete iOS and Android support: text generation, chat, multimodal, TTS, LoRA, embeddings, and more.

MQTT-over-QUIC client for Capacitor (iOS, Android, Web). Native: ngtcp2+WolfSSL; Web: MQTT over WebSocket (WSS), same API.

Run llama.cpp offline in Capacitor apps — GGUF LLMs on iOS, Android, Web/PWA, and Electron with chat, embeddings, multimodal, TTS, and LoRA.

Convert documents to Study PKC v3: MuPDF chunking → binary assets → executor BGE/USearch → SmolLM2