AURA is an open-source interactive AI Avatar project developed by the Advanced Software Engineering (ASE) Laboratory. Inspired by AI VTubers, AURA serves as a virtual assistant capable of answering questions, managing lab information, and providing conversational support via a web portal.
-
Powered by LLMs (OpenAI/Local) with LangChain
-
Semi real-time interactive chatting
-
RAG Knowledge Base
-
Aware of ASE Lab’s history, projects, and members
-
Uses internal documents through vector-based retrieval
-
Text-to-Speech (TTS) and Speech-to-Text (STT)
-
Generates natural, human-like audio responses
React-based dashboard for configuration and monitoring
- Backend: Python, FastAPI, LangChain, ChromaDB
- Frontend: React, TailwindCSS
- Integrations: OpenAI / Gemini / Local LLMs, TTS & STT Service
- Docker & Docker Compose
- Clone the repository:
git clone https://github.com/ASE-Lab/project-aura.git
cd project-aura- Copy the environment file and fill in your API Keys then do:
cp .env.example .env- Run with docker:
Run with Docker
docker-compose up --build- Access:
-
Control Panel: http://localhost:3000
-
API Docs: http://localhost:8000/docs
We follow a standard open-source contribution workflow!
-
Fork the repository.
-
Create a Branch for your feature (git checkout -b feat/add-new-rag-source).
-
Commit your changes.
-
Push to the branch.
-
Open a Pull Request.
See CONTRIBUTING.md for detailed instructions.
Check our GitHub Projects Board for the latest tasks. (Note: Avatar/VTube integration is slated for a future phase).
Distributed under the MIT License. See LICENSE for more information.
Built with ❤️ by the ASE Lab Members