Trending repositories: vision
2 tracked repositories tagged with vision, ordered by stars. Use the topic filters below to narrow further.
Filter by topic
2 of 2 repositories
bytedance/UI-TARS-desktop
The Open-Source Multimodal AI Agent Stack: Connecting Cutting-Edge AI Models and Agent Infra
AI summary: Vision-language model agent for automating complex GUI tasks on desktop operating systems.
38,494productivityTypeScriptApache-2.0StarTrail-org/PixelRAG
The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/
AI summary: Visual retrieval pipeline that renders documents as images to preserve layout for vision-language models.
9,300ai-mlPythonApache-2.0