LLM Harbor
Containerized LLM toolkit. Run LLM backends, APIs, frontends, and additional services via a concise CLI.
High commit volume, frequent releases and growing activity.
Commit activity more than 82% of tracked projects; popularity more than 59%. How this is calculated.
Commits, last 11 months
| Stars | 3.2k |
|---|---|
| Latest release | v0.5.14 · 25 Sept 2026 |
| Repo updated | 25 Sept 2026 |
| Licence | Apache-2.0 |
| Built with | Docker, Shell |
Is LLM Harbor actively maintained?
Over the last 11 months the project absorbed 1179 commits, of which 643 arrived in the most recent quarter — roughly 214 commits a month.
Activity is accelerating: the last quarter carried 58% more commits than the one before it.
The most recent tagged release, v0.5.14, shipped within the last month — a current, installable version exists today.
LLM Harbor ranks #10 of 14 tracked generative artificial intelligence (genai) projects. Several better-maintained options exist in the same category — they are listed below.
What LLM Harbor actually does
LLM Harbor is a containerised toolkit managed through a command-line interface for running large language model backends, APIs, and frontends. It orchestrates multiple GenAI services within a single environment using standard container infrastructure.
Best fit: Self-hosters who want a unified command-line tool to quickly spin up various LLM-related services without configuring each component manually.
Worth knowing: The project relies heavily on shell scripts and container orchestration, which can make debugging complex configuration issues or custom integrations difficult.
Deployment notes
Since it uses Docker and shell scripts, you will typically need a host with Docker installed, persistent volumes configured for model weights and data, and a reverse proxy to handle TLS termination.
Links
LLM Harbor as a replacement for
Alternatives to LLM Harbor
Projects in the same categories, ordered by health score.
Modern design AI chat framework supporting multiple AI providers, one click install MCP Marketplace and Artifacts / Thinking.
User-friendly AI Interface, supports Ollama, OpenAI API.
Run your AI models locally and generate images and audio (alternative to OpenAI and Claude).
Enhanced ChatGPT-compatible AI chat interface supporting multiple AI providers, with multi-user auth, message search, and plugin support.
Chat UI that works with any LLM. It comes loaded with advanced features like agents, web search, RAG, MCP, deep research, Connectors to 40+ knowledge sources, and more.
LLMOps platform for prompt management, LLM evaluation, and observability. Build, evaluate, and monitor production-grade LLM applications with collaborative prompt engineering.