Private on-device AI suite for Android. Fork of Google AI Edge Gallery with llama.cpp, whisper.cpp, stable-diffusion.cpp, GGUF import, voice chat, vision AI, on-device image generation, biometric lock, encrypted history, and NPU/TPU/GPU acceleration.
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Box is a security-hardened fork of Google AI Edge Gallery — with on-device image generation, voice mode (speech-to-speech AI chat), voice input, document analysis, vision AI, biometric lock, encrypted chat history, llama.cpp support, and GGUF model import.
Disclaimer
Box is an independent community fork of Google AI Edge Gallery and is not affiliated with or endorsed by Google LLC. Google branding has been replaced throughout. All credit for the underlying platform goes to Google and the original contributors — this fork simply builds on top of their work.
Related
Built OfflineLLM first — a privacy-first Android chat app with a llama.cpp backend.
This project (Box) forks Google's AI Edge Gallery to create a hybrid LiteRT / llama.cpp feature rich hybrid experience.
→ Try the OfflineLLM app for pure llama.cpp on-device chat.
What is Box?
Box is an Android app for running AI entirely on-device — chat, voice mode, image generation, speech-to-text, document analysis, and vision, all without a network connection. It inherits the full feature set of the upstream Google AI Edge Gallery and layers on top: encrypted conversations, biometric lock, hard offline mode, and three additional native inference engines (llama.cpp, stable-diffusion.cpp, whisper.cpp) alongside LiteRT.
Box: On-Device AI. No Cloud. No Compromise.
What makes Box unique? You can sit at your desk, tap two buttons, and have a real flowing voice conversation with an AI — no wake word, no account, no server, no subscription. It listens, thinks, and speaks back sentence by sentence before it's even finished generating. Point the camera at something and ask about it out loud. The AI sees it and answers. All of it runs on the phone in your hand, completely offline, faster than you'd expect.
I have now created a separate branch called custom-rom-support, along with a corresponding release section specifically for users on third-party operating systems.
If you are using a custom ROM, please use the custom-rom-support
branch/release instead of the main branch. This branch supports TPU/NPU
acceleration on Tensor devices; however, Snapdragon acceleration
remains untested.
Please expect broken features if you are using a custom ROM and running the current release or branch from main. A separate APK and branch (custom-rom-support)
are now available for users on third-party Android operating systems,
including but not limited to LineageOS, GrapheneOS, and CalyxOS.
Note:
The primary reason for these limitations is that third-party operating
systems typically lack AICore and system-level Text-to-Speech (TTS)
components. As a result, features such as voice-to-voice mode and
NPU/GPU acceleration are either unavailable or significantly impaired on
these ROMs.
Screenshots
What Box adds on top of upstream
Box is a fork of Google AI Edge Gallery. The upstream project is excellent — Box just layers on additional capabilities:
| Area | What Box adds |
|---|---|
| Inference engines | llama.cpp (GGUF LLMs), stable-diffusion.cpp (image gen), whisper.cpp (STT) alongside LiteRT |
| Model import | Import any local GGUF file — not limited to the curated download list |
| NPU / TPU | All Snapdragon / Tensor / MediaTek variants bundled in one APK (upstream ships per-SoC) |
| Voice mode / Vision mode| Free talk (continuous hands-free loop) and Vision talk (live camera + voice) |
| Image generation | On-device Stable Diffusion via GGUF |
| Speech-to-text | On-device Whisper STT |
| Document analysis | Attach text files directly in chat |
| Chat history | Persisted to a SQLCipher-encrypted Room database, resumable across sessions |
| Security | Biometric app lock, hard offline mode, prompt sanitisation, audit log |
| Agent skills | 20 built-in skills (upstream has 9) |
| Math rendering | LaTeX expressions rendered as Unicode in chat |
Core Features
Local Chat
Multi-turn conversations with on-device LLMs. Import any GGUF model or download LiteRT models from the built-in list. Supports Thinking Mode on compatible models. Full markdown rendering with LaTeX math support — Greek letters, operators, fractions, and notation are rendered as Unicode symbols. Conversations are persisted and resumable.
Recommended models: We highly recommend Gemma 4 E2B or Gemma 4 E4B (LiteRT) as your primary models — best-tested, support vision, voice, and documents, and run efficiently with GPU/NPU acceleration. Available to download dir
A Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude's agent-sdk), and injects relevant context back into future sessions.
-FF79C6.svg){kind=tracking}
