Private on-device AI chat for Android — runs any GGUF model locally via llama.cpp with ARM-optimised SIMD. Zero network permissions, encrypted settings, biometric lock, tamper detection.

Your AI. Your phone. No cloud. No subscription. No limits. Run powerful language models directly on your Android device , fully offline, completely private.

Run AI on any device. No PC, no subscription, no struggle. Auto-detects your hardware, picks the right model, downloads it, and runs it. Built for people who can't afford cloud AI. Free & open source.

Public lab notes, evidence, patches, and monitoring helpers for QVAC BitNet LoRA on Android Termux

Production KMP framework for Google LiteRT-LM. Run Gemma on-device with OEM-aware RAM fixes, resilient Ktor chunked downloads, and schema-driven function calling. Plain Android support. AGPL-3.0 / Commercial dual-licensed.

Run LLMs on Snapdragon NPU — including the 'unsupported' 8 Gen 1 (Hexagon v69). Verified at 31 tok/s on OnePlus 10 Pro.

Current build: local-qwen-gemma ** Synapse Bridge v0.0.6.2-b is a mobile agent framework for Android. Enables the installation of desktop LLMs or custom agent builds to interact through a secure local MCP-based middleware layer. Includes HTTPS/SSL tunnel capability. Doesn't require root.

Run fully offline private AI chat on Android with on-device LLM inference via llama.cpp and zero network access