kossakovsky/selfhost-ai

One-command installer for a self-hosted AI stack on your own server: n8n, Ollama, Open WebUI, OpenClaw, Dify, Flowise, Supabase, ComfyUI, Qdrant & 30+ tools. Docker Compose, automatic HTTPS via Caddy, built-in monitoring. Free Zapier/Make alternative.

What it solves

It eliminates the complex manual setup required to build a private AI infrastructure. Instead of configuring dozens of separate tools for LLMs, agents, and automation, users can deploy a complete, integrated stack of over 30 open-source AI tools on their own server with a single command.

How it works

The project provides a Docker Compose-based installer and an interactive wizard. The wizard handles the technical heavy lifting: it generates security secrets, configures a Caddy reverse proxy for automatic HTTPS via Let's Encrypt, and allows the user to selectively install specific services. It supports various hardware profiles, including CPU, NVIDIA, and AMD GPUs for local model execution.

Who it’s for

It is designed for users who want a self-hosted alternative to platforms like ChatGPT, Zapier, and Make, and for those building a private AI "homelab" where data privacy is paramount.

Highlights

  • One-Command Deployment: Interactive installation wizard that handles secrets and configuration.
  • Comprehensive Toolset: Includes local LLM runners (Ollama), chat interfaces (Open WebUI), agent builders (Dify, Letta, Keelflow), and RAG engines (RAGFlow, LightRAG).
  • Workflow Automation: Integrated n8n setup with 400+ integrations and optional community workflow imports.
  • Automated Infrastructure: Built-in Caddy reverse proxy for HTTPS and a Grafana/Prometheus monitoring stack.
  • Hardware Flexibility: Supports multi-GPU setups for local inference.

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 templates that simplify the deployment and testing of various AI agent frameworks by automating environment and model configuration.

  • Project
    Osmantic/ODS

    A local AI server stack that provides a one-command installation of inference engines, chat interfaces, and automation tools for private, self-hosted AI.

  • Project
    av/harbor

    Harbor is a CLI and companion app that orchestrates a full local AI stack—back‑ends (Ollama, llama.cpp, vLLM, etc.), front‑ends (Open WebUI, LibreChat, etc.), and auxiliary services (SearXNG, Speaches, ComfyUI, n8n, etc.)—via simple `harbor up` commands. It handles Docker‑Compose generation, cross‑service wiring, profile management, and offers an agentic “Boost” workflow engine for multi‑step coding assistance.

  • Project
    docker/genai-stack

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