Harbor: CLI tool for one-command local LLM stack deployment
By
Ivan Charapanau
5d ago· 2 min readenProduct
55/100
Doughy
Bagelometer↗
A bagel that needed a few more minutes. And maybe a fact-check.
Score55Typepress releaseSentimentpositive
Summary
Harbor is a CLI tool and companion that lets developers spin up complete local LLM stacks with a single command. Created by Ivan over nearly two years, it started as a weekend script to avoid debugging Docker Compose files for local AI projects and grew into a catalog of 129 services. Harbor handles wiring between services like Open WebUI, Ollama, SearXNG, speech tools, and ComfyUI, enabling local AI backends, chat frontends, web search, voice, image generation, fine-tuning, and agent tools to work together out of the box.
Key quotes
· 4 pulledThe core idea is that local AI services should work together out of the box.
harbor up gives you Open WebUI and Ollama. You add more services by name, like harbor up searxng speaches comfyui, and Harbor handles the wiring between them.
It was supposed to be a weekend script, but the problem turned out to be bigger than I thought and it grew into a catalog of 129 services.
Harbor saves you dozens of hours configuring your local AI stack.
Harbor saves you dozens of hours configuring your local AI stack. One command spins up LLM backends, chat frontends, web search, voice, image gen, fine-tuning, agent tools - all pre-configured to talk to each other. Manage your downloaded models, create c
