The magic of Sikuli is its use of the OpenCV library under the hood (and Tesseract for OCR). You could skip the Sikuli part and just use OpenCV and Tesseract directly. (Not easy, but theoretically possible.)
I once used sikuli to extract a table from a pdf. Pretty funny way of hacking a fast solution for a problem. It's a pretty powerful tool but not very stable. IDE is also not so exciting but gets the job done.
Pretty excited to see how far this project will go.
