1.microsoft / OmniParserA simple screen parsing tool towards pure vision based GUI agentJupyter NotebookCC-BY-4.026K total2.2K forks+27 starsfrom 25,578 · score 3.33
2.IDEA-Research / Grounded-Segment-AnythingGrounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anythingopen-vocabulary-detectionopen-vocabulary-segmentationdata-generationautomatic-labeling-systemcaptionspeech+2 moreJupyter NotebookAPACHE-2.018K total1.6K forks+2 starsfrom 17,788 · score 1.10