# 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.

Repository: https://github.com/Mobile-Artificial-Intelligence/maid
Canonical: https://ross.abutalabs.com/products/maid
Language: TypeScript
License: MIT
License Family: permissive
Topics: android, chatbot, chatgpt, facebook, gguf, llama, llama-cpp, mistral, openai, ollama, mobile-artificial-intelligence, claude, deepseek, anthropic
Last push: 2026-07-23T10:02:07+00:00

## Health v2 (maintenance only)
Score: 83/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 94, release rhythm 74, longevity 75
- inputs: {"age_days": 1051, "days_push": 41, "days_rel": 176, "gap_med": 10.0, "n_releases_24m": 9}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2651, forks 281 (observed 2026-08-28T04:07:07.005036+00:00)

## What it is
Maid is a free, open-source Android chat application (built with React Native) for talking to large language models. It runs GGUF models fully on-device via llama.cpp for offline inference, and can also connect to remote providers like Anthropic, DeepSeek, Mistral, Novita, Ollama, and OpenAI with a user-supplied API key.

## Use cases
- chat with local llm on android
- run gguf models offline on my phone
- mobile chatbot client for openai and claude apis
- talk to ollama from my phone
- private ai assistant with no internet required
- download hugging face models and run them on-device
- manage and export llm chat conversations on mobile

## When to choose
- You want to run LLMs entirely offline on an Android device with no data leaving the phone
- You want one mobile app to reach multiple providers (OpenAI, Anthropic, DeepSeek, Mistral, Ollama) using your own API keys
- You want one-tap downloads of curated Hugging Face GGUF models or to load your own GGUF files
- You need conversation import/export as JSON and per-session tuning of temperature, top-p, top-k, and context length

## When to avoid
- You need an iOS, desktop, or web client - Maid is Android-only
- You need built-in text-to-speech, which requires the separate Maise companion app
- You want a library or SDK to embed chat into your own app rather than a ready-to-use application
- You expect the app to include model weights rather than downloading or loading them yourself

## Facets
- artifact type: application
- maturity: active
- function: chatbot, llm-inference, chat-interface
- domain: artificial-intelligence, large-language-models, chatbots, mobile-development
- platform: -
- tags: llama-cpp, gguf, react-native, local-llm, offline-ai, on-device-inference, bring-your-own-key, openai-client, anthropic-client, ollama-client, hugging-face, android, mobile

## Member repositories
- Mobile-Artificial-Intelligence/maid (main) score 83

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:07.005036+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:18:41.389817+00:00, confidence not recorded.
  - readme: https://github.com/Mobile-Artificial-Intelligence/maid (fetched 2026-08-28T04:07:07.005036+00:00, sha c3f27b39648a)
- Data as of 2026-08-30T08:39:29.467469+00:00.