Alternatives to polyrepo-boundaries
polyrepo-boundaries is an agent skill by xberg-io: Decide which xberg-io repository owns a cross-repository fix or API, and coordinate compatible changes across Xberg, Alef, enterprise, crawler, LLM, and OCR…. If it doesn't fit your setup, these 12 agent skills cover similar ground. They are ordered by how closely they match polyrepo-boundaries and by our rank, which weighs adoption, freshness and documentation; money never changes the order. ocr-pipeline-and-quality leads the list (largest repository here (9,441 stars); active in the last 30 days). Each entry shows data reasons to switch, and you can open a side-by-side comparison with polyrepo-boundaries.
Updated Oct 26, 2026 · Built from catalog data; how we rank and grade
You're replacing
polyrepo-boundaries
Decide which xberg-io repository owns a cross-repository fix or API, and coordinate compatible changes across Xberg, Alef, enterprise, crawler, LLM, and OCR…
12 alternatives
Ordered by how closely each matches polyrepo-boundaries (shared product, category or stated alternative) and by rank.
- 1ocr-pipeline-and-quality
xberg-io
Change or evaluate Xberg OCR backends, preprocessing, caching, page acceptance, geometry, hOCR structure, table reconstruction, or cross-backend quality.
- Largest repository here (9,441 stars)
- Active in the last 30 days
★ 9.4KLast active Oct 13, 2026Claude Code, Claude apps, Codex, Cursor +6
AFreshness: A–Security: not graded yet - 2
PaddleOCR text recognition skill using PP-OCRv5 lightweight model.
- Supports Python
★ 2KLast active Sep 15, 2026Claude Code, Claude apps, Codex, Cursor +6
BFreshness: B–Security: not graded yet - 3xberg-extracting-with-ocr
xberg-io
Use when extracting text from scanned PDFs, photographed pages, or images that have no embedded text layer.
- Largest repository here (9,441 stars)
- Active in the last 30 days
★ 9.4KLast active Oct 14, 2026Claude Code, Claude apps, Codex, Cursor +6
AFreshness: A–Security: not graded yet - 4c-screen
daxaur
Capture screenshots and extract text via OCR using `peekaboo`, and capture webcam images using `camsnap`.
- Open source (MIT)
★ 173Last active May 23, 2026Claude Code, Claude apps, Codex, Cursor +6
CFreshness: C–Security: not graded yet - 5law-to-markdown
anbeime
律师助理与法律助手在处理繁杂法条时，当需要将 PDF/Word/TXT 格式的法律规范文件转为结构化 Markdown 时适用。自动完成 OCR 解析、法律层级识别与三阶段保真校验，一键生成排版完美的法条 Markdown 文档及审核报告，让法律文本数字化工作事半功倍。
- Supports Python
★ 8.6KLast active Aug 26, 2026Claude Code, Claude apps, Codex, Cursor +6
BFreshness: B–Security: not graded yet - 6PDF Processing Pro
anbeime
综合办公文员与软件开发工程师当需要批量处理PDF表单、提取表格或进行OCR识别时，使用内置脚本一键完成自动化提取与数据校验，彻底告别繁琐的手动录入，让复杂文档工作流高效、稳健落地。
- Supports Python
★ 8.6KLast active Aug 26, 2026Claude Code, Claude apps, Codex, Cursor +6
BFreshness: B–Security: not graded yet - 7VatInvoiceOCR2Excel
CoderWanFeng
用 OCR 技术识别增值税发票图片并导出到 Excel，支持批量处理和翻译。当用户提到发票识别、增值税发票 OCR、电子发票识别、发票汇总时使用。
- Supports Python
★ 1.4KLast active Aug 4, 2026Claude Code, Claude apps, Codex, Cursor +6
BFreshness: B–Security: not graded yet - 8ocr-and-documents
taracodlabs
Extract text from PDFs, images, scans, and Word documents using Python libraries and CLI tools
- Active in the last 30 days
- Open source (Apache-2.0)
★ 863Last active Oct 19, 2026Claude Code, Claude apps, Codex, Cursor +6
AFreshness: A–Security: not graded yet - 9ocr-translate-skills
wentorai
7 ocr & translation skills.
- Open source (MIT)
★ 306Last active Jun 19, 2026Claude Code, Claude apps, Codex, Cursor +6
CFreshness: C–Security: not graded yet - 10literature-pdf-ocr-library
LigphiDonk
Search traceable academic papers, download legally accessible PDFs from arXiv and open-access sources, convert PDFs or page images to Markdown with a…
- Supports Python
★ 747Last active Apr 15, 2026Claude Code, Claude apps, Codex, Cursor +6
DFreshness: D–Security: not graded yet - 11ocr-local
gon9
ローカル Tesseract OCR でスクリーンショット画像群を Markdown に文字起こしする。Playwright による自動スクショ取得も可能。社外秘ドキュメントを外部 API に出さずに処理したいときに使う。
- Supports Python
Last active Sep 27, 2026Claude Code, Claude apps, Codex, Cursor +6
AFreshness: A–Security: not graded yet - 12doctr
VectorSpaceLab
Use python-doctr (docTR) for OCR/KIE inference, document IO/export, model customization, datasets/training/evaluation, CLI helpers, deployment, and…
- Supports Python
★ 341Last active Sep 2, 2026Claude Code, Claude apps, Codex, Cursor +6
BFreshness: B–Security: not graded yet