Markup Relay：面向AI编程智能体的开源视觉标注工具发布
英文摘要
SUB&SUB studio has released Markup Relay, an open-source browser-based tool that lets users annotate images and videos to help AI coding agents understand visual context. Files can be dragged in and annotated with a selection tool; unselected areas are automatically blurred. For videos, keyframes are extracted to describe dynamic changes. Processed files are uploaded to Cloudflare R2 and automatically deleted after a set time. The team is seeking feedback via ProductHunt.
中文摘要
SUB&SUB 工作室发布了开源工具 Markup Relay，可通过浏览器对图像和视频进行标注，帮助 AI 编程智能体理解视觉上下文。用户可拖入文件，用框选工具标记关注区域，未框选部分自动模糊；视频则提取关键帧描述动态变化。处理后文件上传至 Cloudflare R2 并在设定时间内自动删除，团队正通过 ProductHunt 收集反馈。
关键要点
SUB&SUB studio released Markup Relay, an open-source visual annotation tool.
SUB&SUB 工作室推出了开源视觉标注工具 Markup Relay。
Supports drag-and-drop editing, region selection with automatic blurring, and keyframe extraction from video.
支持拖拽编辑、框选区域自动模糊以及从视频中提取关键帧。
Files are temporarily uploaded to Cloudflare R2 and auto-deleted after a preset time.
文件临时上传至 Cloudflare R2，并在预设时间后自动删除。
Aims to fill the gap when AI coding agents lack visual design modes or need step-by-step visual guidance.
旨在弥补 AI 编程智能体缺少可视化设计模式或需要逐步视觉引导的缺口。