tightwad by youngharold

Gradio based tool to run opensource LLM models directly from Huggingface. Maintained by Aesthisia on GitHub, where it has earned 99 stars from the community.

AI commit messages from your local LLM - Ollama / llama-cpp backed, offline, Conventional Commits, with review + changelog modes. Maintained by yumiaura on GitHub, where it has earned 39 stars from the community.

The whole local AI stack in one executable: it runs and manages local AI models across every GPU, and it's a search engine you can talk to, with cited answers from your files, code, and the web. MCP server for coding agents, web crawler, TUI, CLI, REST API, Python library. No Ollama or LM Studio needed, works with both. Maintained by tobocop2 on GitHub, where it has earned 43 stars from the community.