Ame is a State-of-the-art, multi-modal virtual assistant framework powered by LLaMA

Ame is a State-of-the-art, multi-modal virtual assistant framework powered by LLaMA

Ame, a powerful, feature-rich, multi-modal, open-source virtual assistant framework, is designed to run locally and is powered by LLaMA. It can operate on both enterprise-grade and consumer-grade hardware, with split computing planned for future versions.

Work in Progress

However, Ame is still in development, with slow progress expected due to a single developer working on it. Audio file communication between the client and server has not been implemented yet.

Key Features

Customizable Modules

Ame's modular design allows for easy customization and extensibility. Each module serves a specific function, such as managing calendars, providing updates, or assisting with personal tasks—Ame adapts to you. Developers can create their own modules or modify existing ones to tailor Ame's capabilities to their specific requirements.

Text-to-Speech (TTS) and Speech-to-Text (STT):

Ame's TTS and STT capabilities enable natural and effortless communication. STT is powered by OpenAI's whisper and TTS is powered by Suno's bark.

Discord & Telegram Integration:

Ame seamlessly integrates with both Discord and Telegram, allowing you to interact with it through text-based messaging and voice notes. Discord and Telegram provide a familiar and convenient way to interact with Ame, enabling efficient communication and access to its full range of functionalities.

Open-Source:

Ame is entirely open-source. This allows for knowledge sharing and the continuous improvement of Ame while contributing to the open-source community, democratizing ML research in the process.

Locally Run and Privacy-Focused:

Ame prioritizes user privacy and data control by operating entirely on the user's local machine or a user controlled server.

Long-term Memory:

Ame utilizes a vector database that optimizes memory storage and retrieval, enabling Ame to access data that goes beyond the context limit of its model.

Other Features

  • Support for any LLaMA GGML/GGUF (via llama.cpp)
  • Developer-friendly module platform
  • Long-term memory
  • Full customizability
  • High-quality text-to-speech (via bark)
  • Accurate speech-to-text (via whisper)
  • Smart context limit management
  • Pre-built server and client
  • Remote server command
  • Client UI*
  • Telegram integrations*
  • Discord integrations*
  • Fully open-source
  • Easy-to-use API

Tech

  • Python

License

Ame is released under the MIT License, which allows you to use, modify, and distribute the software freely.

Resources & Downloads

GitHub - Expl0dingCat/Ame: State-of-the-art, multi-modal virtual assistant framework powered by LLaMA. Ame’s core is complete, some minor features are still in development.
State-of-the-art, multi-modal virtual assistant framework powered by LLaMA. Ame’s core is complete, some minor features are still in development. - Expl0dingCat/Ame