# PDFMathTranslate/PDFMathTranslate

[EMNLP 2025 Demo] PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 等服务，提供 CLI/GUI/MCP/Docker/Zotero

Repository: https://github.com/PDFMathTranslate/PDFMathTranslate
Canonical: https://ross.abutalabs.com/products/pdfmathtranslate
Homepage: https://pdf2zh.com
Language: Python
License: AGPL-3.0
License Family: copyleft
Topics: chinese, latex, pdf, translation, korean, english, japanese, openai, pdf2zh, russian, python, translate, math, zotero, obsidian, document, edit, modify, mcp
Last push: 2026-08-26T21:57:03+00:00

## Health v2 (maintenance only)
Score: 69/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 40, longevity 51
- inputs: {"age_days": 726, "days_push": 7, "days_rel": 418, "gap_med": 3, "n_releases_24m": 22}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 36368, forks 3247 (observed 2026-08-28T04:12:01.041457+00:00)

## What it is
PDFMathTranslate (pdf2zh) is a tool that translates scientific PDF documents while preserving the original layout, including formulas, charts, tables of contents, and annotations. It supports multiple translation services (Google, DeepL, Ollama, OpenAI) and is available as a CLI, GUI, Docker image, and MCP server.

## Use cases
- translate a scientific paper pdf to chinese while keeping formulas intact
- batch translate pdf documents with deepl or openai
- produce bilingual pdf translations of academic papers
- translate pdfs from the command line
- integrate pdf translation into zotero or obsidian workflow
- self-host a pdf translation service with docker

## When to choose
- you need layout-preserving translation of scientific or technical PDFs
- you want formula, chart, and table of contents preservation in translated PDFs
- you want flexible choice of translation backends including local LLMs via Ollama
- you need CLI, GUI, Docker, or MCP integration options

## When to avoid
- you need to translate scanned PDFs without a text layer
- you need translation of non-PDF formats like Word or EPUB
- you need pixel-perfect translation of highly complex magazine-style layouts
- you need a fully managed cloud service with no setup

## Facets
- artifact type: cli-tool
- maturity: active
- function: nlp, pdf, llm-inference, cli, gui
- domain: pdf, developer-tools
- platform: python, cross-platform, cli
- tags: pdf-translation, layout-preserving, bilingual, deepl, zotero, mcp, scientific-papers, natural-language-processing, localization, docker, web-server

## Member repositories
- PDFMathTranslate/PDFMathTranslate (main) score 69

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:01.041457+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:26:15.712038+00:00, confidence not recorded.
  - readme: https://github.com/PDFMathTranslate/PDFMathTranslate (fetched 2026-08-28T04:12:01.041457+00:00, sha eba33a1b4339)
  - homepage: https://pdf2zh.com (fetched 2026-08-29T07:47:34.358627+00:00, sha 44136fa355b3)
- Data as of 2026-08-30T08:39:29.467469+00:00.
