Maid is a cross-platform free and an open-source application for interfacing with llama.cpp models locally, and remotely with Ollama, Mistral, Google Gemini and OpenAI models remotely. Maid supports sillytavern character cards to allow you to interact with all your favorite characters. Maid supports downloading a curated list of Models in-app directly from huggingface.

Maid utilises git submodules extensively. To clone the repository, use the following command:

git clone --recursive https://github.com/Mobile-Artificial-Intelligence/maid.git

Maids repository has flutter linked as a submodule. This is needed for reproducible fdroid builds. However, for development you may want to use a local install of flutter. Remove the flutter submodule by running the git command

git submodule deinit -f packages/flutter

To install the dependencies on fedora based systems, use the following command:

sudo dnf install -y cmake ninja-build pkg-config gtk3-devel vulkan-devel

To install the bdependencies on debian based systems, use the following command:

sudo apt-get install -y cmake ninja-build pkg-config libgtk-3-dev libvulkan-dev

Windows, MacOS, Linux, Android. Releases page. IOS Releases not available at this time.

• Write code comments
• Documentation
• Testing and Building on IOS
• Spreading the word
• Google Play Testing

• ggerganov/llama.cpp
• ollama/ollama
• davidmigloz/langchain_dart
• Mobile-Artificial-Intelligence/maid_llm
• Mobile-Artificial-Intelligence/babylon_tts
• Mobile-Artificial-Intelligence/babylon.cpp

MacOS version tested on a Android version tested on a Oneplus 10 Pro 11gb phone. Also tested on Fedora Linux, Windows 11. Tested with calypso 3b, orcamini 3b, minyllama 1.1b, phi 3, mistral 7b, mixtral 8x7b, llama 2 7B-Chat, llama 7B and many more.

Maid is distributed under the MIT licence and is provided without warranty of any kind, express or implied. Maid is not affiliated with Huggingface, Meta (Facebook), MistralAi, OpenAI, Google, Microsoft or any other company providing a model compatible with this application.

This project is licensed under the MIT License.