Malaika isn't just a companion, she's a presence. Inspired by the minimalist elegance of "Her" and the high-energy aesthetic of modern social interfaces, Malaika combines a 3D persona with a cutting-edge neural architecture. No sidebars, no clutter just one immersive screen where classical beauty meets the edge of what's possible.
Frontend
Backend
Tools & Platforms
- Python 3.9+
- Node.js 18+
- Docker & Docker Compose
- Hugging Face API Token
frontend/: Contains the React application with TypeScript and Three.js 3D rendering.backend/: Contains the FastAPI backend with ChromaDB memory integration.
- Navigate to the
backenddirectory:cd backend - Install the required Python packages:
pip install -r requirements.txt
- Set your Hugging Face API key as an environment variable:
export HUGGINGFACE_API_KEY='your_huggingface_api_key'
- Run the backend server:
uvicorn app.main:app --reload --port 8000
- Navigate to the
frontenddirectory:cd frontend - Install the required npm packages:
npm install --legacy-peer-deps
- Start the React development server:
npm start
- Run with Docker Compose:
docker-compose up --build
- Multi-modal Memory: Integrated with ChromaDB for hybrid semantic/chronological retrieval of conversations.
- Proactive Visual Awareness: Powered by Moondream2 for visual context awareness.
- Emotional Depth: Dual-layered emotion engine analyzing facial expressions and message sentiment.
- Natural Speech Synthesis: Edge-TTS with natural prosody and conversational flow.
- Open your web browser and navigate to
http://localhost:3000. - Interact with Malaika through voice or text.
- Experience a living, breathing AI companion.
This project is licensed under the MIT License.
If you have any questions or issues, please open an issue on GitHub or contact mwalyangashadrack@gmail.com