Jarvis is a comprehensive AI-powered smart home and assistant platform that combines advanced AI capabilities with Home Assistant integration. Built with a modern tech stack, Jarvis provides a complete solution for smart home automation, AI model management, knowledge base systems, and more.

• Full Home Assistant API implementation
• Real-time device control and monitoring
• Entity, device, and area/room registry management
• Event-driven architecture with comprehensive state tracking
• Statistics and historical data analysis

• Multi-provider AI model support (OpenAI, Ollama, Anthropic, Google GenAI)
• Model registry with versioning and provider management
• Pipeline system for complex AI workflows
• Evaluation arena for model comparison and testing

• Real-time WebSocket communication
• Context-aware conversations with memory persistence
• Multi-user chat channels and group management
• Rich message formatting and file attachments

• Intelligent document retrieval and search
• Vector database integration (ChromaDB, Qdrant, Pinecone)
• Content extraction from multiple file formats
• Web search integration with multiple providers

• Audio transcription and text-to-speech
• Image generation and processing
• Video processing capabilities
• Content analysis and tagging

• Comprehensive RESTful API with automatic documentation
• WebSocket support for real-time updates
• Extensible plugin architecture
• Role-based access control and authentication

• Framework: Next.js 15 with React 19
• Styling: Tailwind CSS with Radix UI components
• State Management: React Hooks and Context API
• Real-time: Socket.IO client for WebSocket communication
• UI Components: Custom dashboard with responsive design

• Framework: FastAPI 0.118.0
• Database: SQLAlchemy ORM with multiple database support
• Authentication: JWT-based with OAuth and LDAP support
• Caching: Redis integration
• AI Libraries: LangChain, Transformers, OpenAI, Anthropic SDKs
• Search: ChromaDB, Qdrant, Pinecone vector databases

• Core Models: Users, Chats, Messages, Files, Folders
• AI Models: Models, Pipelines, Functions, Tools
• Home Assistant: States, Events, Statistics, Entity Registry
• Knowledge: Documents, Collections, Retrieval systems
• Media: Audio, Images, Videos with metadata

• Python 3.8+
• Node.js 18+
• Docker (recommended for dependencies)
• PostgreSQL, MySQL, or SQLite database

1. Clone the repository:

git clone https://github.com/your-username/jarvis.git
cd jarvis

2. Backend setup:

# Create virtual environment
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install Python dependencies
pip install -r requirements.txt

3. Frontend setup:

# Install Node.js dependencies
npm install

4. Environment configuration:

# Copy and configure environment variables
cp .env.example .env
# Edit .env with your configuration

Development Mode:

# Start backend server
python start.py

# In a separate terminal, start frontend development server
npm run dev

Production Mode:

# Build frontend
npm run build

# Start server
python start.py

The application will be available at:

• Frontend: http://localhost:3000
• Backend API: http://localhost:8080
• API Documentation: http://localhost:8080/docs

Jarvis provides comprehensive API documentation automatically generated by FastAPI:

• Swagger UI: http://localhost:8080/docs
• ReDoc: http://localhost:8080/redoc

• User registration and login
• JWT token management
• OAuth integration
• Role-based access control

• State management APIs
• Event handling and firing
• Service call execution
• Registry management (entities, devices, areas)
• Statistics and recording

• Model listing and creation
• Provider integration (OpenAI, Ollama, Anthropic)
• Pipeline execution and management
• Model evaluation and comparison

• Message sending and retrieval
• Channel and group management
• File sharing and attachments
• Real-time updates via WebSocket

• Document upload and processing
• Vector search and retrieval
• Collection management
• Content extraction and analysis

Run the test suite with pytest:

pytest tests/

Jarvis can be compiled into standalone executables for Windows, Linux, and macOS that include both the frontend and backend:

• Python 3.8+
• Node.js 18+
• All development dependencies installed

1. Universal Build (Recommended):

python build-all.py

2. Platform-Specific Builds:

• Windows: build-windows.bat
• Linux: build-linux.sh
• macOS: build-macos.sh

For detailed instructions, see BUILDING.md.

The executable will:

• Start the FastAPI backend on port 8080
• Build and serve the Next.js frontend on port 3000
• Run both services as a single application

Jarvis is highly configurable through environment variables. Key configuration options include:

• Database: Multiple database backends supported
• AI Providers: OpenAI, Anthropic, Ollama, Google GenAI
• Vector Stores: ChromaDB, Qdrant, Pinecone, Elasticsearch
• Authentication: JWT, OAuth, LDAP
• File Storage: Local, S3, Azure Blob, Google Cloud Storage

We welcome contributions to Jarvis! Please see our Contributing Guidelines for details on how to get started.

1. Fork the repository
2. Create a feature branch
3. Commit your changes
4. Push to the branch
5. Create a Pull Request

This project is licensed under the MIT License - see the LICENSE file for details.

• Home Assistant community for inspiration
• FastAPI and Next.js teams for excellent frameworks
• Open source AI libraries and tools
• All contributors to the project

For support, please open an issue on GitHub or contact the development team.