Hey everyone! 👋
I have been working on Sightline CRDT, an open in-browser tool for machine learning and computer vision teams to collaboratively audit and fix training bounding boxes without merge conflicts.
How it works:
• P2P Multiplayer: Powered by Yjs CRDTs over WebRTC so multiple auditors can inspect the same image simultaneously with zero merge conflicts.
• Voice Patching: Speak verbal commands like "Nudge box left" to correct coordinates and labels hands-free.
• Export Ready: Full COCO and YOLOv8 export directly from browser memory.
Try the live sandbox:
https://sightline-crdt.netlify.app
GitHub repository:
https://github.com/joshuageoschool2020-cmyk/sightline-crdt
I would love to hear your thoughts and feedback!
30 sec video- https://streamable.com/42wwsf
Top comments (0)