GraphNeT, a deep learning framework for neutrino telescopes, provides a shared library for deep learning experts and neutrino physicists needing advanced deep learning techniques for their analyses. GraphNeT is a detector-agnostic framework, making it easy and intuitive to apply deep learning techniques from one experiment to another and to export models to the physicists who rely on them. GraphNeT lowers technical barriers, enabling physicists to utilize deep learning without extensive expertise, and sets the stage for inter-experimental collaboration.