CLI appAI and agent development
harbor
Launch a pre-wired local LLM stack and supporting services with one command.
- Stars
- 3,141
- Forks
- 211
- Updated
- Updated Jul 14, 2026
Apache-2.0
Launch a pre-wired local LLM stack and supporting services with one command.
Harbor is a CLI and companion app that assembles local model backends, chat interfaces, and supporting services through preconfigured Docker Compose integrations. Users choose components such as Ollama, llama.cpp, vLLM, Open WebUI, SearXNG, speech, or image tools and start them together with a single command, while Harbor centralizes configuration and logs. It is intended as a local LLM development and experimentation environment rather than a production deployment platform.
Resource types
Use cases
Platforms
Runs isolated MCP servers behind a Docker CLI gateway for multiple AI clients.
Assess agent skills, compile structured contracts, and record execution proof.
Runtime
Capabilities
Audience
Public GitHub facts last synced Jul 14, 2026.
Install, pin, and sync shared agent skills across a team’s AI tools.
Search, install, test, and sync agent skills across many AI coding tools.