I really think that too. This space is driven by non open-source labeling tools without any possibility for customization. really appreciate that we see something like that as an open-source project. Will definitely bring this space in the right direction.
A short time ago I was looking for a way to automatically create screenshots and then enter them into the OpenAI API and use the new Vision API.
After I found a solution for this, I wrote a blog article about how I did it. This is the first part, about creating the screenshots.
Maybe it will help some of you.
All the best.