Show HN: Local task classifier and dispatcher on RTX 3080
Summary
This Show HN presents a local, offline 7B LLM task orchestrator that runs on RTX 3080/4090 GPUs to analyze urgency, debate task assignments, and balance load. It includes a self-contained demo with quick-start steps to run a local LLM service, an orchestrator API, and a NiceGUI interface, enabling offline AI-driven task routing for small teams or businesses.