GUI Agents and Automation
10 repos
Systems and frameworks for building AI agents that interact with graphical user interfaces through screen understanding, element grounding, and automated task execution. This includes tools for GUI vision/grounding, agent orchestration, and training data annotation for visual UI understanding. Repositories in this cluster span desktop automation, web UI interaction, and the foundational datasets and models needed to teach agents to navigate and control GUI applications.
agent ·67
GUI ·56
code ·43
Computer_Use ·42
GUI Agent ·42
GUI Grounding ·42
