This is a pretty old project, started long before AI hype. It's still very cool, but I wonder why no one wrote something similar using all the advancements in CV that we have now.
The challenge with Tesseract is that its OCR quality is (too) low for screenshots because screenshots are usually text on colored background. Tesseract is optimized for classical text document OCR. Of course, you can switch OCR engines with Sikuli (I did that before), but this requires touching the source code.