Animius is an open source software library for creating deep-learning-powered virtual assistants. It provides an intuitive workflow that extracts data from existing media (such as anime and TV shows) and trains on them to provide a personalized AI. The flexible architecture enables you to add custom functionality to your virtual assistant.
It is based on python and Tensorflow (with heavy reliance on the 1.x layer architecture).
# Extensions
There are also other projects surrounding the base engine, such as clients and middleware.
- animius-anywhere - WIP mobile client built with Vue Native and Socket.IO
- animius-link - Python middleware providing additional functions like weather and other API calls
- animius-ui - Electron & Vue desktop client integrating animius with Live2D support (repo currently not available)