Ross ROSS = Recommend OSS · open-source software intelligence for agents

wxyhgk/retain-pdf

在保留版面、公式与结构的前提下进行 PDF 翻译,适用于科研与技术文档 observed · 2026-10-13

github.com/wxyhgk/retain-pdf · Python · MIT (permissive) observed · 2026-10-13

Health v2 · maintenance only

82/100

  • Activity 99
  • Release rhythm 98
  • Longevity 14
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-10-21. Adoption (stars, forks) is never an input.

  • gap_med: 0.0
  • age_days: 205
  • days_rel: 14
  • days_push: 8
  • n_releases_24m: 53

Full methodology

Adoption not part of the score

2580 stars · 291 forks observed · 2026-10-13

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

RetainPDF is an open-source PDF translation tool that preserves layout, formulas, and document structure, with special support for scanned/image-based PDFs and complex inline formulas. It ships as desktop apps for Windows/macOS/Linux and a Docker-deployable web service with OCR, translation, and typesetting modules.

Use cases

  • translate scientific papers while keeping the original layout
  • translate scanned or image-based PDFs
  • preserve inline math formulas when translating PDFs
  • batch translate technical documentation with custom translation rules
  • self-host a PDF translation service for a team via Docker
  • compress translated PDFs and control font sizes

When to choose

  • you need layout-preserving translation of scanned PDFs or complex formulas
  • you want a self-hosted or API-driven PDF translation pipeline
  • you translate scientific or technical documents regularly

When to avoid

  • you only need plain text extraction or translation without layout
  • you need a lightweight CLI-only tool
  • you require a fully offline solution without any model/API dependencies

Facets

application · maturity active

ocr pdf nlp machine-learning image-processing pdf files education windows self-hosted cross-platform pdf-translation layout-preserving scanned-pdfs scientific-papers typst document-ai translation natural-language-processing localization macos linux docker

1 source

Member repositories

RepositoryRoleHealth v2
wxyhgk/retain-pdfmain82

For agents

markdown · JSON · MCP: product_card(name="wxyhgk/retain-pdf")

Data as of 2026-10-19T08:05:51.212177+00:00 · Report a problem