scan-to-vector open-sourced: AI agent reconstructs scanned pages
Understand this story
The author has released scan-to-vector, an Agent skill for clients such as Claude Code and Codex that can read SKILL.md, used to reconstruct scanned book pages, manuals, and diagrams into searchable PDFs with diagrams converted to vector paths, and to overlay and check each page against the scan. The author says reconstructing each page takes several minutes and consumes model time; Tesseract by default recognizes only English and requires additional language packs; this is a workflow for agents to execute, not a one-click converter; deleting source files or publishing results only happens when the user requests it.
AI overview based on source reports · Updated 2 days ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Hacker News AIShow HN: Scan-to-vector – rebuild scanned pages as vector PDFs with an AI agent
Scan-to-vector is an agent skill for Claude Code, Codex and other clients that read SKILL.md, which rebuilds scanned pages as searchable PDFs with text, vector-redrawn diagrams and charts, and labelled raster crops, checking each page against the scan via a ledger and overlay review. The author reports benchmarks on unseen documents where all four tested models scored higher with the skill on long documents (Haiku 5.5 from 0.841 to 0.997, Sonnet 5.5 finishing 37% faster), while noting the benchmark is synthetic printed English pages and the workflow takes minutes per page. It is installed via a Claude Code plugin or install.sh, requires Python 3.10+ with PyMuPDF, Pillow, numpy, scipy and tesseract, and is released under the MIT License.
Activity for this story
- Current comparable activity
- 3
- Peak comparable activity
- 10Nov 4 23:00
- Change in the past 24 hours
- -49%
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.