Blind people already use AI to use 2D UIs, but they have to jump through hoops to verify the output. This project makes verification easier using WebMCP, so blind users get AI's full benefit.
I update the video and description to put a finer point on the screen reader collaboration features, and also shipped a bunch of screen reader enhancements around tree grid for arrow key support, as well as allowing keyboard command to create connections between nodes.
Log in or sign up for Devpost to join the conversation.