kossakovsky/selfhost-ai

🚀 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

It simplifies the deployment of a complex, private AI ecosystem. Instead of manually configuring dozens of separate tools for LLMs, agents, and automation, this project provides a single-command installation process to set up a fully integrated, self-hosted AI workshop on a VPS.

How it works

The project uses a Docker Compose template and an interactive installation script. It automates the system preparation, Docker installation, and the configuration of a Caddy reverse proxy for automatic HTTPS. Users can select which services they want from a curated list of over 30 tools—including local LLM runners, vector databases, and workflow automation platforms—which are then deployed as isolated containers that communicate over a private network.

Who it’s for

It is designed for developers, AI enthusiasts, and homelabbers who want full control over their AI data and operations without the overhead of manual infrastructure setup.

Highlights

  • One-Command Deployment: An interactive wizard handles secrets, domain configuration, and service selection.
  • Caddy Integration: Automatic Let's Encrypt SSL certificates for all deployed services.
  • Comprehensive AI Stack: Includes tools like Ollama for local LLMs, n8n for automation, Flowise and Dify for agents, and Qdrant/Weaviate for vector storage.
  • Built-in Monitoring: Integrated Grafana and Prometheus stack with specialized dashboards for tracking workflow performance.
  • Scalable Architecture: n8n is deployed in queue mode with Redis and Postgres to handle high-volume parallel processing.

Related

  • Project
    n8n-io/self-hosted-ai-starter-kit

    A Docker Compose template that bundles n8n, Ollama, and Qdrant to quickly set up a self-hosted, local AI development environment for building AI agents and workflows.

  • Project
    docker/compose-for-agents

    A collection of Docker Compose demos for deploying and orchestrating AI agents, supporting multiple frameworks and local or remote model execution.

  • Project
    Osmantic/ODS

    A local AI server stack that provides a one-command installation of inference, chat, RAG, and agent tools for private AI on your own hardware.

  • Project
    docker/genai-stack

    A Docker-based starter stack for building GenAI applications, featuring integrated LLMs and Neo4j for RAG and knowledge graph capabilities.

  • Project
    livecontext-ai/livecontext-ce

    LiveContext CE is an open‑source, self‑hosted AI automation platform that turns a single chat prompt into a full workflow, scoped LLM agents, data tables and tiny web apps. It bundles a visual workflow engine, AI agents with per‑agent budgets, 700+ built‑in integrations, and optional browser‑rendering add‑ons, all deployable via a single Docker‑Compose stack.