LLaMa-MCP-Streamlit by Nikunj2003

A minimal AI agent built from scratch — no agent framework, just Python, the OpenAI SDK, and a `while` loop. Accompanies the Medium article "Build Your Own AI Agent from Scratch." Three execution modes: `local` (Ollama only), `remote` (cloud provider), `mixed` (local orchestrates, delegates to remote). Maintained by sergenes on GitHub, where it has earned 26 stars from the community.

Export and Backup Ollama models into GGUF and ModelFile. Maintained by AaronFeng753 on GitHub, where it has earned 99 stars from the community.

Run LLMs locally with as little friction as possible. Maintained by leftmove on GitHub, where it has earned 121 stars from the community.