Harbor
ActiveDescription
One command brings a complete pre-wired LLM stack with hundreds of services to explore and build AI applications.
Key Features
- One-command local LLM stack deployment with pre-wired Docker Compose orchestration
- Hot-swappable backends: Ollama, llama.cpp, vLLM, and more
- Integrated frontends: Open WebUI with built-in RAG, TTS/STT capabilities
- Extensible service ecosystem: SearXNG web search, Speaches voice chat, ComfyUI image generation
- Companion GUI app for visual management alongside the CLI
- Zero manual configuration — cross-service connectivity handled automatically
Use Cases
💡 Rapidly spin up a local AI development environment for experimentation
💡 Build private LLM-powered applications without cloud dependencies
💡 Run web search-augmented AI assistants with SearXNG integration
💡 Generate images locally using ComfyUI alongside LLM inference
💡 Set up voice-enabled AI chatbots with TTS/STT support
Strengths & Limitations
✅ Strengths
- • Actively maintained, recent updates
- • High community interest (3.2k stars)
- • Permissive open-source license (Apache-2.0)
- • Established track record (2 years in production)
Categories
Quick Start
```bash
# Install Harbor CLI
brew install av/tap/harbor # macOS
# Start the full LLM stack
harbor up
# Add web search and voice chat
harbor up searxng speaches
```
Access Open WebUI at http://localhost:33801