Item detail

av/harbor

av/harbor is an Apache-2.0-licensed, open-source CLI and companion app that brings up a complete local LLM stack with a single command, pre-wiring backends like Ollama, llama.cpp, and vLLM with frontends like Open WebUI and supporting services like SearXNG for web search, Speaches for voice chat, and ComfyUI for image generation, so AI hobbyists, developers, and local-AI users can run a fully conf

Score7.6
Popularity7.3
Risklow
TierGold
Score breakdown
Usefulness8.0
Novelty7.0
Momentum7.0
Maturity6.2
Open-source/build8.4
Evidence7.2
Workflow potential8.7
Setup ease8.8

Popularity is tracked separately. Support, ads, sponsorships, and tips never affect these signals.

Why it matters

Useful for AI hobbyists, local-AI developers, and self-hosters who want a turnkey local LLM stack, because Harbor ships a CLI plus companion app that pre-wires Ollama, llama.cpp, vLLM, Open WebUI, SearXNG, Speaches, and ComfyUI under Docker Compose with cross-service connectivity, which means a complete local AI stack can be up and running with `harbor up` instead of writing and maintaining a cust

Who should use it

AI hobbyists and local-AI developers who want a turnkey local LLM stack without writing Docker Compose filesSelf-hosters who need Ollama, llama.cpp, vLLM, Open WebUI, SearXNG, Speaches, and ComfyUI pre-wired togetherTinkerers who want a CLI plus companion app to start, stop, and inspect a local AI stack

Who should skip it

Skip if the source link, docs, or setup requirements do not match your workflow.

Risk explanation

It runs Ollama, llama.cpp, vLLM, Open WebUI, SearXNG, Speaches, and ComfyUI under Docker Compose on the host, so audit which ports are exposed, lock down which services are reachable from outside the host, and validate that downloaded model weights come from the providers you intend before promoting to a shared self-hosted deployment.

Evidence links

Closest alternatives / related signals

local-llmollamallama-cppvllmopen-webuidocker-composeself-hostedapache-2.0