[Apple Reportedly Developing Local AI Model Execution App] According to a report by Gelongbao, sources have revealed that Apple is developing a Mac application called Harbor, which can turn computers equipped with Apple chips into private AI inference servers. It supports direct downloading, management, and execution of open-weight models without uploading data to the cloud. The application can also connect two or more compatible Macs via Thunderbolt 5, automatically forming a cluster and consolidating unified memory to run large models exceeding single-machine capacity or handle more concurrent requests, without manual configuration or command-line usage. The application is currently in closed preview by Apple's software company Claris, and a formal release date has not yet been announced.