Selfhost AI
A Docker Compose installer that deploys a private, self-hosted AI and automation stack, including n8n, Ollama, Open WebUI, OpenClaw, Dify, Flowise and Supabase, onto a server with one command.
Selfhost AI is an interactive installer that deploys more than thirty open-source AI and automation tools onto a single server as a private homelab. It bundles local large-language-model serving through Ollama on CPU, NVIDIA or AMD GPUs, a ChatGPT-style chat interface through Open WebUI with an optional code-execution sandbox, workflow automation through n8n with hundreds of integrations and scalable worker queues, several AI agent and retrieval-augmented-generation tools including OpenClaw, Flowise, Dify, Letta, LightRAG and RAGFlow, vector databases such as Qdrant and Weaviate, and Grafana and Prometheus monitoring with a ready-made dashboard and alerts.
An interactive setup wizard chooses which of the optional services to install, generates every secret automatically, and places everything behind a Caddy reverse proxy with automatic HTTPS through Let's Encrypt or an optional Cloudflare Tunnel; PostgreSQL and a Redis-compatible store are always installed as shared infrastructure. It is aimed at running on an Ubuntu server with a public IP, a domain and a wildcard DNS record pointed at that server.
It is written in Shell and released under the Apache-2.0 license.