# av/harbor

Stop configuring your AI stack. Start using it. One command brings a complete pre-wired LLM stack with hundreds of services to explore.

Repository: https://github.com/av/harbor
Canonical: https://ross.abutalabs.com/products/av-harbor
Homepage: https://discord.gg/8nDRphrhSF
Language: Python
License: Apache-2.0
License Family: permissive
Topics: cli, docker, docker-compose, llm, tools, ai, self-hosted, tool, bash, container, local, npm, package, pypi, safetensors, mcp, automation, homelab, server
Last push: 2026-08-16T12:40:33+00:00

## Health v2 (maintenance only)
Score: 85/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 98, release rhythm 86, longevity 54
- inputs: {"age_days": 767, "days_push": 17, "days_rel": 17, "gap_med": 2, "n_releases_24m": 116}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3191, forks 223 (observed 2026-08-28T04:07:48.172318+00:00)

## What it is
Harbor is a CLI tool that spins up a complete, pre-wired local LLM stack with a single command, using Docker Compose to orchestrate hundreds of AI services. It removes the manual configuration burden of assembling self-hosted AI tooling.

## Use cases
- spin up a local LLM stack with one command
- self-host AI services without manual docker-compose configuration
- explore and try out hundreds of AI tools locally
- set up an MCP-enabled AI environment in a homelab
- quickly provision a pre-wired AI development environment
- run local AI services without configuring each component

## When to choose
- you want a full local AI/LLM stack running quickly without hand-writing compose files
- you run a homelab or self-hosted setup and want to explore many AI services
- you want a CLI-driven, reproducible way to launch pre-integrated AI tooling

## When to avoid
- you need fine-grained, production-grade control over every service configuration
- you only need a single specific AI tool rather than a whole stack
- you cannot run Docker or lack the hardware for local LLM workloads

## Facets
- artifact type: cli-tool
- maturity: active
- function: cli, llm-inference, mcp, deployment, container-orchestration, developer-tools, self-hosted
- domain: large-language-models, developer-tools, self-hosted
- platform: cli, python, windows, self-hosted
- tags: docker-compose, llm-stack, homelab, one-command-setup, ai-tooling, local-ai, ai-agents, command-line, docker, linux, macos

## Member repositories
- av/harbor (main) score 85

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:48.172318+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:45:00.041985+00:00, confidence not recorded.
  - readme: https://github.com/av/harbor (fetched 2026-08-28T04:07:48.172318+00:00, sha 1b89d690651c)
  - homepage: https://discord.gg/8nDRphrhSF (fetched 2026-08-29T09:38:42.356633+00:00, sha 6f9d4f441f34)
- Data as of 2026-08-30T08:39:29.467469+00:00.