This project provides a comprehensive, self-hosted AI development environment using Docker Compose, integrating Ollama for local LLMs, Open WebUI for a chat interface, Supabase for database and vector storage, and n8n for low-code workflow automation. It targets developers and power users looking to build and manage local AI applications efficiently, offering a unified platform with over 400 integrations.

How It Works

The package leverages Docker Compose to orchestrate multiple AI services, including Ollama, Supabase, Open WebUI, Flowise, Langfuse, SearXNG, and Caddy. A Python script (start_services.py) simplifies deployment and GPU configuration (Nvidia, AMD, CPU, or none). Supabase acts as a central hub for data, vectors, and authentication, while n8n provides a visual interface for building complex AI workflows with pre-built AI nodes and integrations.

Quick Start & Requirements

• Install: Clone the repository, navigate to the directory, and run python start_services.py --profile <gpu-nvidia|gpu-amd|cpu|none>.
• Prerequisites: Python, Git, Docker/Docker Desktop.
• Configuration: Requires setting environment variables in a .env file for n8n, Supabase, and Langfuse secrets.
• Docs: Original Local AI Starter Kit, Cole's Guide

Highlighted Details

• Integrates n8n with over 400 integrations and AI components.
• Includes Supabase for database, vector store, and authentication.
• Supports local LLMs via Ollama with GPU acceleration options.
• Provides Open WebUI for a ChatGPT-like interface.
• Adds Flowise for no/low-code AI agent building.
• Incorporates Qdrant for high-performance vector storage.
• Features SearXNG for private internet search and Caddy for managed HTTPS.
• Includes Langfuse for LLM observability.

Maintenance & Community

• Curated by n8n-io and coleam00.
• Community forum available via oTTomator Think Tank.
• GitHub Kanban board for feature implementation and bug tracking.

Licensing & Compatibility

• Licensed under Apache License 2.0.
• Compatible with commercial use and closed-source linking.

Limitations & Caveats

The starter kit is designed for proof-of-concept projects and may require customization for production environments. GPU support on Mac/Apple Silicon is limited to CPU or external Ollama instances. Ensure no "@" symbol is present in Supabase Postgres passwords to avoid connection issues.