Harbor

A command-line tool and app that starts a complete, pre-wired local AI stack, such as Ollama and Open WebUI with search and voice, in one command.

3.3k stars, 233 forks Python On GitHub since July 2024

Visit website View on GitHub How to run it

What is Harbor?

Harbor saves you from writing Docker Compose files for a local AI setup. You pick services, such as back ends like Ollama, llama.cpp or vLLM, front ends like Open WebUI, SearXNG for web search, Speaches for voice and ComfyUI for images, and harbor up starts them already connected to each other. It handles configuration and networking between containers, and a desktop app for macOS, Windows and Linux adds a graphical way to manage the stack. Hundreds of services are available.

Good fit if

  • You want to try many local AI tools without configuring each one.
  • You switch between inference engines and want them wired to the same front end.

Look elsewhere if

  • You need only one model server: install Ollama directly.
  • You want a single app with everything built in: AnythingLLM.

Before you adopt it

Harbor is Apache-2.0, with no paid parts. It needs Docker, and almost every commit comes from its author, so it depends on one person.

Drafted with AI from the project's README and repository data, then checked against that data on 30 October 2026. Report a correction

Harbor health: is it still maintained?

80 of 100, actively developed

  • Activity
    206 commits in the last 90 days, the latest on 31 October 2026.
    28 / 30
  • Contributors
    6 people wrote the latest 100 commits; the most active wrote 94% of them.
    11 / 20
  • Releases
    15 releases in the last 12 months; the latest, v0.5.19, on 31 October 2026.
    19 / 20
  • Replies to issues
    Maintainers answered 89% of recent issues, with a median first reply after 2 days.
    17 / 20
  • Security practices
    No OpenSSF Scorecard for this repository yet, so this part gets a neutral score.
    5 / 10

Read from GitHub on 1 November 2026. How the score works

Harbor license: is it open source?

Harbor uses Apache-2.0, an open-source license approved by the OSI.

  1. July 2024First published on GitHub.
  2. TodayApache-2.0.

How to run Harbor yourself

Docker
Dockerfile or compose file in the repository
Compose file
compose.yml
Setup effort
1 of 5, judged from the compose file
Kubernetes
No Helm chart in the repository
Desktop and mobile
Builds for macOS, Linux, Windows, including ARM in GitHub releases
Interface languages
English only

Install instructions: discord.gg or the README on GitHub.

Alternatives to Harbor

  • Open WebUIUser-friendly AI Interface (Supports Ollama, OpenAI API, ...) 76 health · Open WebUI License · 157k stars
  • OnyxOpen Source AI Platform - AI Chat with advanced features that works with every LLM 77 health · MIT · 33.1k stars
  • LocalAILocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware.… 75 health · MIT · 50.1k stars
  • GPT ResearcherAn autonomous agent that conducts deep research on any data using any LLM providers 74 health · Apache-2.0 · 30.4k stars
  • DocsGPTPrivate AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research,… 84 health · MIT · 18.4k stars

All 36 projects in AI chat & local LLMs

Questions about Harbor

Is Harbor open source?

Yes. Harbor is published under Apache-2.0, an OSI-approved open-source license.

Is Harbor still maintained?

Its health score is 80 of 100 (actively developed). It had 206 commits in the last 90 days, the latest on 31 October 2026, and its latest release came out on 31 October 2026.

How do I run Harbor?

You can run it with Docker, as an app for macOS, Linux, Windows, including ARM. The README on GitHub has the exact steps.

What are the alternatives to Harbor?

Close alternatives in the AI chat & local LLMs category include Open WebUI, Onyx, LocalAI.