Back to directory

Maid - Mobile Artificial Intelligence Distribution

A free, open-source Android app for chatting with LLMs, running GGUF models locally via llama.cpp or connecting to remote providers such as Anthropic, DeepSeek, Ollama, and OpenAI.

Maid - Mobile Artificial Intelligence Distribution

Maid is a free and open-source Android application for interfacing with large language models, either fully on-device or through a remote API. It runs GGUF model files locally through llama.cpp with no internet connection required, or connects to remote providers including Anthropic, DeepSeek, Mistral, Ollama, and OpenAI using the user's own API key.

It offers one-tap downloads of curated Hugging Face models such as Qwen, Phi, and TinyLlama, or loading any GGUF file from local storage, alongside conversation management with export and import as JSON, per-session generation parameters such as temperature and context length, a custom system prompt and assistant persona, and optional account sync for backing up settings and chat history. A companion app adds text-to-speech voice output.

It is built with React Native, distributed for Android, and released under the MIT license, with no telemetry or ads.

More in Inference

See all 770
  • OpenDecision

    deepanwadhwa.github.io

    An open-source Python package that answers typed questions about application state or documents using a local natural-language-inference model, returning structured choice, score, yes/no or evidence-relation values instead of free text.

  • Lifeboat

    iterate.ai

    A local inference server that puts an OpenAI- and Anthropic-compatible API in front of open-weight language models running on hardware you control, from a laptop to a GPU cluster.

  • Claude S40

    github.com

    An unofficial Claude chat client for 2007-era Nokia Series 40 phones, built as a Java ME app plus a small Go relay server, with web search, reading mode and saved chats.