A multi-modal desktop assistant that acts as a true action-oriented operator. It bridges the gap between live conversation, computer vision, local OS management, and physical 3D hardware control using the Google Gemini Native Audio API.

1. Clone the repository:

   git clone https://github.com/ks9128/aria.git
   cd aria

2. Environment Setup: Create a .env file in the root folder with your API key:

   GEMINI_API_KEY=your_google_api_key_here

3. Start the Backend (Python 3.11):

   pip install -r requirements.txt
   python backend/server.py

4. Start the Frontend (Node/React):

   npm install
   npm run dev

Built with 🤖 by Khalid Saifullah