Clippy’s paperclip grin is back on the desktop — not as an official Microsoft resurrection, but as a DIY homage that runs entirely on your PC using local LLMs and the open-source LLM inference stack. What started as a nostalgic tinkering project has become a practical, privacy-conscious way to run lightweight assistants on Windows 11: an Electron-based wrapper that downloads compact models, chooses the most efficient inference backend (Metal, CUDA, Vulkan, or CPU), and speaks with the cheeky...