#149 · Primary category： Inference & Local Deploy
Box
The most advanced, fully offline client-side AI suite on Android today.
Project last updated：08/24/26
GitHub Stars
791
Forks
48
Contributors
1
License
Other
Why we included this project
Box is an Android app that runs a full set of AI tools locally, so you can talk to an LLM, read documents and photos, generate images, transcribe audio, and make music without any connection to the network. It builds on llama.cpp, whisper.cpp, and stable-diffusion.cpp, imports models in GGUF format, and can offload work to the NPU or TPU on recent Snapdragon, Tensor, and MediaTek chips, which is what makes private AI practical on hardware you already carry. The biometric lock and encrypted chat history back up the offline posture, and the RAG and vision features keep it from being just another chatbot. For anyone who wants a self-contained local AI setup instead of a cloud subscription, it is worth a look.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
ollama
Get up and running with Kimi-K2.6, GLM-5.2, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
llama.cpp
LLM inference in C/C++
vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
gpt4all
GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.
LocalAI
LocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.