README.md

Artificial Intelligence Companion that actually says things.

Malaika isn't just a companion, she's a presence. Inspired by the minimalist elegance of "Her" my favorite movie, and the high energy aesthetic of modern social interfaces.

Tech Stack

Frontend

Backend

Tools & Platforms

Quick Start

Prerequisites

• Python 3.9+
• Node.js 18+
• Docker & Docker Compose
• Hugging Face API Token

Project Structure

• frontend/: Contains the React application with TypeScript and Three.js 3D rendering.
• backend/: Contains the FastAPI backend with ChromaDB memory integration.

Setup and Installation

Backend

1. Navigate to the backend directory:

   cd backend

2. Install the required Python packages:

   pip install -r requirements.txt

3. Set your Hugging Face API key as an environment variable:

   export HF_TOKEN='your_huggingface_token'

4. Run the backend server:

   uvicorn app.main:app --reload --port 8000

Frontend

1. Navigate to the frontend directory:

   cd frontend

2. Install the required npm packages:

   npm install --legacy-peer-deps

3. Start the React development server:

   npm start

Docker Setup (Alternative)

1. Run with Docker Compose:

   docker-compose up --build

Features

• Multi-modal Memory: Integrated with ChromaDB for hybrid semantic/chronological retrieval of conversations.
• Proactive Visual Awareness: Powered by Qwen2.5-VL-7B-Instruct for high-fidelity visual and video 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.

Usage

1. Open your web browser and navigate to http://localhost:3000.
2. Interact with Malaika through voice or text.
3. Experience a living, breathing AI companion.

License

This project is licensed under the MIT License.

Support

If you have any questions or issues, please open an issue on GitHub or contact mwalyangashadrack@gmail.com