Harbor
SHA-256A CLI and app to effortlessly spin up a complete local LLM stack with one command.
Smart Download
Download Download Version
v0.4.15 · 122.4 MB
One command to launch a full local LLM stack with zero config.
Core Features
- One-click startup: Single `harbor up` command launches all services, no manual Docker Compose editing
- Modular selection: Supports Ollama, llama.cpp, vLLM and more, mix and match as needed
- Rich integrations: Built-in Open WebUI, web search (SearXNG), voice chat (Speaches), image generation (ComfyUI)
- Pre-configured connectivity: Services automatically discover each other, no need to set API addresses
- Graphical management: Companion Harbor App offers a GUI for those who prefer not to use CLI
What It Can't Do
- •Requires Docker (Windows/Mac/Linux). First launch will pull Docker images and models – needs internet and may take time. Default ports may conflict; adjust in configuration. Harbor is under active development; some services may be unstable.
Use Cases
- Run LLMs like Llama or Mistral locally without relying on cloud APIs
- Build a private AI workstation with search, voice, and image generation capabilities
- Quickly set up a LLM dev/test environment for developers, avoiding complex container orchestration
Harbor is a command-line tool and companion app that lets you deploy a fully integrated local LLM environment in seconds. It orchestrates Docker Compose to run backends like Ollama, llama.cpp, or vLLM, frontends like Open WebUI, and supporting services such as SearXNG for web search, Speaches for voice chat, and ComfyUI for image generation. Everything is pre-configured to work together out of the box—no manual setup, no wiring. Just pick the services you need and run `harbor up`. Harbor also provides a graphical app for managing services and settings, making local AI accessible to anyone.
Tags
Getting Started
Download installer
Click the button above to download the installer for your system
Install the software
Install the appropriate package for your distro (dpkg / rpm / AppImage)
Step 1: Install Docker if you haven't already
Step 2: Download and install Harbor CLI (or use Harbor App) – see Wiki installation guide
Step 3: In terminal, run `harbor up` to start the default stack (Ollama + Open WebUI)
- Step 1: Install Docker if you haven't already
- Step 2: Download and install Harbor CLI (or use Harbor App) – see Wiki installation guide
- Step 3: In terminal, run `harbor up` to start the default stack (Ollama + Open WebUI)
SHA-256 checksum verified
Checksum extracted from GitHub official Release page
SHA256 Checksum
02cef91e460d0a061dd564eab01535c1c812078ddb2d4df167b1a3394b69702aThis checksum is extracted from the GitHub Release page. Verify file integrity after download.
All SHA-256 checksums on this platform are extracted from the project's official GitHub Release page, without any modification. You can independently verify them on the GitHub Releases page.
Open Source Transparency
View GitHub SourceUninstall Info
Remove the Harbor directory (default ~/.harbor) and run `docker compose down` to clean up containers. For a full cleanup including images, run `docker system prune -a`.
No Extra Dependencies
Ready to use after download. No additional runtime required.
Having issues? Check the FAQ below
4 FAQs
Similar Projects
ollama
Ollama lets you download, run, and manage large language models locally. One command, multiple platforms, endless possibilities.
llama.cpp
High-performance LLM inference engine in C/C++ with minimal dependencies, supporting quantized models (1.5–8 bit) and diverse hardware (Apple Silicon, CUDA, Vulkan, etc.).
mempalace
Open-source local-first AI memory system with verbatim storage and semantic search — zero API calls, no keys, top benchmark scores.