#pdf-ocr · Dev Tools

PDF & OCR

Read, edit and convert PDFs and scanned documents, from parsers and OCR to document-to-Markdown tools.

This week (Oct 27 – Nov 2), the top-ranked are MiniCPM-OCR (+754), OXR (+1,941) and Xiaomi-OCR-0 (+539). The 113 ranked repos gained 18,955 stars, 15% more than the week before.

Updated Nov 2, 07:32 UTC · ranked every hour from GitHub’s daily star counts

Updated 17 min ago

GitHub topic ↗

This week’s ranking

Showing 10 of 113

How Upstar ranks

1
OpenBMB/MiniCPM-OCR Fast, accurate OCR with correctness assessment. TypeScript TypeScript · 754 total New
Gained in 7 d +754 Score 75.4 Total 754
2
SoMarkAI/OXR An open-source document parsing model with SOTA accuracy and speed, using an RSI loop during post-training. Python Python · 2.9k total Spotted at 257 stars
Gained in 7 d +1.9k Score 64.1 Total 2.9k
3
xiaomi-research/Xiaomi-OCR-0 Xiaomi-OCR-0 Python Python · 651 total
Gained in 7 d +539 Score 50.9 Total 651
4
yjid/kensaku Search inside documents, code, and even screenshots - instantly and locally. A free, open-source file launcher with OCR, semantic search, and MCP agent access. Rust Rust · 497 total
Gained in 7 d +497 Score 49.7 Total 497
5
IceWhaleTech/filens 📄 Office / PDF / iWork / CAD / 3D / RAW / 360° 🔒 Browser-local preview & conversion 🤖 Agent CLI with OCR, structured text & layout extraction ⚡ Rust + WebAssembly 🧩 Vue 3 integration. Open-source, local-first. Your files, your device. TypeScript TypeScript · 329 total
Gained in 7 d +327 Score 32.7 Total 329
6
scott20201225/marknote-pro 本地优先的结构化 Markdown 笔记与知识工作台。原生集成 Git 版本控制、Draw.io 绘图、GeoGebra 建模、思维导图、KDBX 密码库（含 2FA & SSH 直连）及 PDF 专业批注。| Local-first structured Markdown notes & knowledge base with Git, Draw.io, GeoGebra, MindMap, KDBX & PDF. JavaScript JavaScript · 322 total Mixed signals
Gained in 7 d +274 Score 27.4 Total 322
7
Forward-Future/folio Folio — a simple, clean, open-source PDF reader for Windows TypeScript TypeScript · 262 total New
Gained in 7 d +262 Score 26.2 Total 262
8
datalab-to/indra 1M param OCR model - runs on CPU, 15x faster than tesseract, close to 1B+ param models in accuracy Python Python · 1.6k total Spotted at 636 stars
Gained in 7 d +460 Score 13.7 Total 1.6k
9
strugglesky/scrubshot 粘贴一张截图，它找出手机号、身份证、银行卡、Token、地址，一键涂掉。图片全程留在浏览器里——不上传、不联网、可断网使用。 TypeScript TypeScript · 115 total
Gained in 7 d +112 Score 11.2 Total 115
10
xristosstarnetgames439-del/HuiwenMCP 开源鸿蒙PC应用项目。Qt + OpenHarmony / HarmonyOS PC 文档阅读、编辑与格式转换项目，集成 ArkTS、CEF 浏览器内核、PDFium 与 Python HNP。已支持 PDF/Markdown 双栏预览、同步滚动、PDF 转 Markdown 与最近工作区恢复；规划支持 Word 文档预览与编辑、PDF 编辑、Markdown 编辑、OCR 文字识别及多格式批量转换。源码公开，供学习交流与教学参考，欢迎提交 Issue、通过 PR 贡献代码，共同完善鸿蒙 PC 文档工具。自有代码采用 PolyForm Noncommercial 1.0.0 许可。 C++ C++ · 236 total
Gained in 7 d +118 Score 10.9 Total 236

Emerging in PDF & OCR Past weeks: Oct 26 Oct 19