av/harbor
One command brings a complete pre-wired LLM stack with hundreds of services to explore.
Orchestrates Docker Compose-based multi-service deployments with pre-configured integrations between LLM backends (Ollama, llama.cpp, vLLM), frontends (Open WebUI), and specialized services like SearXNG for web search, Speaches for voice I/O, and ComfyUI for image generation. Uses a service catalog and automatic configuration management to eliminate manual wiring of cross-service connectivity. Available as both a CLI tool and companion application across Node.js, Python, and Docker ecosystems.
2,498 stars. Actively maintained with 57 commits in the last 30 days.
Stars
2,498
Forks
168
Language
TypeScript
License
Apache-2.0
Category
Last pushed
Mar 12, 2026
Commits (30d)
57
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/av/harbor"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
containers/ramalama
RamaLama is an open-source developer tool that simplifies the local serving of AI models from...
RunanywhereAI/runanywhere-sdks
Production ready toolkit to run AI locally
runpod-workers/worker-vllm
The RunPod worker template for serving our large language model endpoints. Powered by vLLM.
vtuber-plan/olah
Self-hosted huggingface mirror service. 自建huggingface镜像服务。
foldl/chatllm.cpp
Pure C++ implementation of several models for real-time chatting on your computer (CPU & GPU)