av/harbor

One command brings a complete pre-wired LLM stack with hundreds of services to explore.

66
/ 100
Established

Harbor helps developers quickly set up a complete local environment for building and experimenting with Large Language Models (LLMs). With a single command, you get pre-configured LLM backends like Ollama and frontends like Open WebUI, plus supporting tools for web search, voice interaction, and image generation. This is ideal for AI/ML engineers, researchers, or anyone prototyping LLM applications who needs a full local stack without complex manual setup.

2,498 stars. Actively maintained with 83 commits in the last 30 days.

Use this if you need a fully integrated, local development environment for building and testing AI applications with various LLMs and related services without the hassle of individual installations and configurations.

Not ideal if you're looking for a cloud-based solution or a simple API to access pre-trained models without needing a local development stack.

AI development Machine learning engineering LLM prototyping Local AI infrastructure AI research environment
No Package No Dependents
Maintenance 22 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

2,498

Forks

168

Language

TypeScript

License

Apache-2.0

Last pushed

Mar 12, 2026

Commits (30d)

83

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.