Self-host n8n-install
v1.18.2One-command AI stack installer with n8n, Ollama, Open WebUI
- Stars
- 953
- CPU
- 2 CPU cores
- RAM
- 4 GB RAM
- Storage
- 40 GB disk
- Ports
- 80 (HTTP (redirects to HTTPS)), 443 (HTTPS (Caddy reverse proxy with automatic Let's Encrypt))
- Requires
- Caddy, PostgreSQL, Valkey (Redis-compatible)
What is n8n-install?
Selfhost AI installs a full AI homelab on your own server using Docker Compose. An interactive wizard chooses which of the 30+ services to run, generates every secret, and wires them behind Caddy with automatic Let's Encrypt certificates. The stack includes n8n for workflow automation, Ollama for local LLM inference, Open WebUI as a ChatGPT-style chat, AI agents such as OpenClaw, Flowise, Keelflow, Dify and Letta, RAG engines like LightRAG and RAGFlow, vector databases Qdrant and Weaviate, Supabase as a Firebase alternative, ComfyUI and InvokeAI for image generation, and Grafana/Prometheus for monitoring. It runs on Ubuntu 24.04 LTS with a public IP and a domain; minimum resources are 4 GB RAM and 2 CPU cores for the core services, or 20 GB RAM and 4 CPU cores for everything. The project is Apache 2.0 licensed with no vendor lock-in.
Should you self-host n8n-install?
n8n-install scores 57/100 on selfhost.directory (how scoring works) and ranks #2 of 10 in AI Automation. It has 953 GitHub stars.
It shipped 21 stable releases in the past year. The latest, v1.18.2, came out on 27 October 2026. New versions land roughly every 5 days.
Setup is moderate: expect some configuration beyond a single command. It is Apache-2.0-licensed and written mostly in Shell.
Its closest alternative on selfhost.directory is openhands (87/100, 92 086 stars). It scores higher overall, so compare the two before you pick. See n8n-install vs openhands side by side.
Features
- AI agents and RAG
- Automatic HTTPS
- Built-in monitoring
- ChatGPT-style web interface
- Document processing and OCR
- Image Generation
- Local LLM Inference
- Low-code app builders
- One-command installation
- Production-Ready
- Social media automation
- Translation API
- Web search and scraping
- WhatsApp Integration
- Workflow Automation
n8n-install README
More in Local AI
nekoniNekoni is a self-hosted, open-source AI agent running locally via Ollama with P2P WebRTC phone access, RAG, skills automation, and Ed25519 auth.
obrew-studio-serverSelf-hosted, open-source AI engine that runs LLMs locally with RAG, agents, and workflow automation — no cloud dependency, all data stays on your device.
Ollama GUIOpen-source, self-hosted single-page chat front end for models served by your own Ollama, with streamed answers, vision uploads, model pulling and browser-side history.
ollama-intel-gpuA self-hosted Docker image running Ollama on Intel Arc GPUs via IPEX-LLM, drop-in replacement for Nvidia Ollama with same API on port 11434.
OvertChatSelf-hosted AI chat with local models, bundled voice/search, multi-user accounts, native mobile/desktop apps, and portable SQLite database.
PHOBOSSelf-hosted AI OS running LLMs, image/video generation, web browsing, audio, and tasks locally with no cloud.
PrivateDocBotPrivateDocBot is a self-hosted, open-source chatbot for querying PDF documents locally using LLMs like Llama 2 via Chainlit.
ReameSelf-hosted LLM server for CPU inference using ternary models, runs 8B models in 2.2GB RAM on free-tier ARM with OpenAI-compatible API.
SelenaCoreSelf-hosted offline smart home hub for Pi/Jetson with local voice (Vosk, Piper, Ollama), modular providers, automations, energy monitoring, multilingual UI — no cloud.
self-hosted-ai-starter-kitThis open-source Docker Compose template spins up a self-hosted AI stack with n8n, Ollama, Qdrant and PostgreSQL, auto-pulling Llama3.2 for local workflows.
ShimmyA self-hosted, open-source LLM inference server: a single Rust binary that serves GGUF models through an OpenAI-compatible API, as an alternative to Ollama.
sidixSIDIX is a free, open-source AI agent on Qwen2.5-7B with LoRA. 35 tools, Raudah multi-agent, continuous LoRA retraining, IHOS provenance. Hosted discontinued Aug 2026.
0 comments