Harbor is a command-line interface (CLI) and companion application designed to simplify the deployment of local Large Language Model (LLM) stacks. With a single command, users can set up various backends, including Ollama, llama.cpp, and vLLM, as well as frontends like Open WebUI. It integrates supporting services such as SearXNG for web search and Speaches for voice interactions, streamlining the orchestration and configuration process through Docker Compose. The application is categorized under AI Automation and is freely available for use on the MCP platform.

The program provides features such as local inference capabilities for LLMs, voice chat setups, and a user-friendly CLI for managing configurations and command history. Advanced functionalities include profile management for different LLM configurations, built-in tunneling for remote access, and the ability to generate images using integrated tools. Harbor is designed for ease of use, making it suitable for both experienced users and those new to LLM technology.