kossakovsky/n8n-install

🚀 Self-hosted AI automation platform. Deploy n8n, Ollama, Flowise, RAG, Supabase & 30+ tools with one command. Auto HTTPS. Free Zapier/Make alternative.

What it solves

Setting up a comprehensive, private AI environment is complex, requiring multiple interconnected services like LLM engines, vector databases, and workflow automation tools. This project simplifies that process by providing a single-command installer for a complete, self-hosted AI workshop.

How it works

The project uses a Docker Compose template and an interactive installation wizard to deploy a suite of tools on an Ubuntu 24.04 LTS server. It automates system preparation, security hardening, and secret generation. It uses Caddy as a reverse proxy to provide automatic HTTPS for all services. The installer allows users to select specific tools from a curated list, including local LLM runners, vector stores, and agent builders, and can even import hundreds of pre-built community workflows.

Who it’s for

It is designed for individuals and developers who want to build a private AI homelab or production-ready AI applications without vendor lock-in, ensuring full control over their data and infrastructure.

Highlights

  • Comprehensive Toolset: Deploys a wide range of services including Ollama (local LLMs), n8n (automation), Flowise (agent building), and various vector databases like Qdrant and Weaviate.
  • Scalable Architecture: Configures n8n in queue mode with Redis and Postgres for robust parallel processing.
  • Integrated Monitoring: Includes a Grafana and Prometheus stack to track system performance.
  • User-Friendly Interface: Provides Open WebUI for a ChatGPT-like experience with local models.
  • Automated Security: Features automatic HTTPS via Caddy and optional Cloudflare Tunnel support for zero-trust access.