Mattin AI is a comprehensive AI toolbox that provides a wide range of artificial intelligence capabilities and tools. This project offers various AI functionalities including:

• Large Language Models (LLMs) integration and management
• Retrieval-Augmented Generation (RAG) systems
• Semantic search capabilities
• Vector database management
• AI agents and automation
• And more...

The project aims to simplify the integration and use of AI technologies, providing a unified platform for various AI-powered solutions.

• LLM Integration: Easy access and management of various Large Language Models
• RAG Systems: Implementation of Retrieval-Augmented Generation for enhanced AI responses
• Semantic Search: Advanced search capabilities using semantic understanding
• Vector Databases: Efficient storage and retrieval of vector embeddings
• AI Agents: Framework for building and deploying AI agents
• Modular Architecture: Easy to extend and customize for specific needs

• Python 3.11 or higher
• Node.js 18 or higher
• PostgreSQL with pgvector extension
• Docker and Docker Compose (optional)

1. Clone the repository:

   git clone https://github.com/your-username/ia-core-tools.git cd ia-core-tools

2. Set up the backend:

   cd backend cp env.example .env # Edit .env with your configuration pip install -r requirements.txt

3. Set up the frontend:

   cd frontend npm install

4. Set up the database:

   # Using Docker Compose (recommended) docker-compose up -d postgres # Or install PostgreSQL with pgvector manually

5. Run the application:

   # Backend cd backend python main.py # Frontend (in another terminal) cd frontend npm run dev

The easiest way to get started:

# Copy environment file cp backend/env.example .env # Edit .env with your configuration # Start all services docker-compose up -d

Key environment variables you need to configure:

• DATABASE_*: PostgreSQL database configuration
• OPENAI_API_KEY: Your OpenAI API key
• ANTHROPIC_API_KEY: Your Anthropic API key
• SECRET_KEY: Secret key for session management
• GOOGLE_CLIENT_ID / GOOGLE_CLIENT_SECRET: Google OAuth credentials

See backend/env.example for a complete list of configuration options.

The platform supports multiple AI providers:

• OpenAI (GPT models)
• Anthropic (Claude models)
• Azure OpenAI
• Mistral AI
• Ollama (local models)

Configure these through the web interface or environment variables.

The project consists of several main components:

• Backend: FastAPI-based REST API with Python
• Frontend: React-based web interface with TypeScript
• Database: PostgreSQL with pgvector for vector storage
• AI Services: Modular integration with various LLM providers

We welcome contributions! Please see our Contributing Guidelines for details.

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests if applicable
5. Submit a pull request

• Full Documentation
• API Documentation
• Deployment Guide

This project is available under a dual licensing model:

• Open Source: GNU Affero General Public License v3.0 (AGPL 3.0)
• Commercial: Proprietary license with enhanced rights and features

• Free to use for development and personal use
• Community contributions welcome
• Source code disclosure required for network use
• Copyleft obligations for modifications

• Full AICT functionality without restrictions
• Commercial use rights without copyleft obligations
• Client modification rights for specific projects
• Enterprise features and support
• No source code disclosure requirements

For more information, see:

• LICENSING.md - Detailed licensing information
• COMMERCIAL_LICENSE.md - Commercial license terms
• CLIENT_LICENSE_AGREEMENT.md - Client agreement template

Contact LKS Next for commercial licensing inquiries.

• Create an issue for bug reports or feature requests
• Check the documentation for common questions
• Join our community discussions

• Built with FastAPI
• Frontend powered by React
• Vector operations with pgvector
• AI integrations via LangChain