Unverified50% confidenceFactExact time
该项目主张用纯文本捕获替代图像捕获，直接将屏幕文本内容提取并保存为 Markdown 格式作为屏幕记忆方案
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/27/2026
First Seen
Valid until: 11/25/2026
Sources
Related Entities
Related Claims
UnverifiedA project named 'Screen memory without screenshots, just text to Markdown' was posted in the Show HN section of Hacker News, advocating for extracting and saving text content from the screen directly as Markdown format without relying on screenshots.78% similarUnverifiedThe visual model receives each screenshot and outputs structured information, including OCR-recognized text, page layout, pixel coordinate bounding boxes of UI controls, and element states.71% similarUnverifiedMainstream screen memory tools almost all adopt a 'continuous screenshot' technical approach — taking a screenshot every few seconds and then performing content recognition through OCR or multimodal models.67% similarUnverifiedThe project outputs editable reMarkable native handwriting vector data rather than static images, which users can further edit.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/809360API
curl https://kongchang.com/api/v1/knowledge/claims/809360MCP
get_claim(id=809360)