Clippy is a local LLM chat application built with Electron that wraps llama.cpp to run various open-source models in GGUF format directly on the user’s machine. It supports one-click installation for models including Gemma3, Llama 3.2, Phi-4, and Qwen3, automatically selecting the best hardware acceleration available (Metal, CUDA, Vulkan). The app deliberately recreates the look and feel of the 1990s Microsoft Office Clippy assistant as both nostalgia and software art. It also serves as a reference implementation of the @electron/llm library.