Mobile-Artificial-Intelligence/maid

Maid is a free and open source application for interfacing with llama.cpp models locally, and with Anthropic, DeepSeek, Ollama, Mistral and OpenAI models remotely.

What it solves

Maid provides a way to run large language models (LLMs) directly on an Android device or connect to remote AI providers, eliminating the need for a constant internet connection for local models and offering a unified interface for multiple AI services.

How it works

Built with React Native, the app uses llama.cpp to perform local inference on GGUF model files. It also integrates with various remote APIs (such as OpenAI, Anthropic, and DeepSeek) using API keys. Users can download curated models from Hugging Face directly within the app or load their own local GGUF files.

Who it’s for

Android users who want to interact with AI models privately on-device or manage multiple remote AI providers through a single, user-friendly mobile application.

Highlights

  • Local and Remote Inference: Run GGUF models fully on-device or connect to providers like Mistral, Novita, and Ollama.
  • Model Management: One-tap downloads for curated Hugging Face models and support for custom local GGUF files.
  • Conversation Tools: Ability to create, rename, export, and import chats as JSON.
  • Customization: Per-session tuning for temperature, top-p, top-k, and context length, plus custom system prompts.
  • Privacy-focused: Fully open source with no ads or telemetry.

Related

  • Dispatch
    LLM Inference on Edge: Running Local LLMs via React Native

    Hugging Face provides a comprehensive guide to building a privacy-focused mobile application using React Native and llama.rn to run quantized GGUF models locally on Android and iOS.

  • Project
    orailnoor/cross-platform-llm-client

    A cross-platform AI chat client that unifies local on-device LLM inference via llama.cpp with cloud API access for OpenAI, Anthropic, and Google Gemini.

  • Project
    Vali-98/ChatterUI

    A native mobile frontend for LLMs that allows users to run models on-device using llama.cpp or connect to various commercial and open-source APIs.

  • Project
    google-ai-edge/gallery

    A mobile and macOS application for running open-source LLMs locally on-device, providing a private and offline environment to experience and evaluate generative AI.

  • Project
    Taewan-P/gpt_mobile

    A multi-provider AI chat client for Android that allows users to interact with various LLMs and deploy on-device agents with tool-calling capabilities.