#3434th of 64 in Data and scraping for AIFor data and documents, documents and ocr
kordoc
Parses HWP, HWPX, PDF and Office files into Markdown, as library, CLI and MCP server
- Stars
- 2.9k
- License
- MIT
- Last commit
- Nov 2026
- Last release
- Nov 2026
- Language
- TypeScript
Missed the latest GitHub check; these facts may be older.
Overview
kordoc converts Korean government document formats (HWP 3.x/5.x, HWPX, HWPML) plus PDF, XLS/XLSX, DOCX, PPTX and images into Markdown and structured blocks. It also writes HWPX from Markdown, converts HWP to HWPX, fills forms and lints documents. It runs as a Node.js library, a CLI, and an MCP server with 22 tools, with local CPU OCR and an offline mode.
Who it is for: Developers feeding Korean HWP/HWPX and PDF documents into RAG or AI agents
Strengths
- Reads HWP/HWPX without Hancom Office; 10,342/10,342 tables matched on 2,424 HWPX files
- Local OCR on CPU with no API key; KORDOC_OFFLINE=1 blocks all external network calls
- Emits RAG chunks with heading paths, plus Python and Java SDKs
- Also generates HWPX from Markdown, converts HWP to HWPX, and fills forms
Weaknesses
- README is written in Korean; an English version is linked separately
- OCR table structure matched only 33 of 65 tables in its own benchmark
- Parallel batch conversion with --jobs increases memory use
- HWP to HWPX conversion fully matches only 69 of 232 compared pairs
What it needs
- no GPU
- Needs Node.js 20+
- Models: HWP 3.x/5.x, HWPX, HWPML, PDF, XLS/XLSX
Also in Data and scraping for AI
See all 64| Rank | Project | Score |
|---|---|---|
| 1 | doclingPython library that converts PDFs, Office files and more into structured text | 93 out of 100 |
| 2 | mineruParses PDFs, images and Office files into Markdown and structured JSON | 91 out of 100 |
| 3 | opendataloader-pdfPDF parser that outputs Markdown, JSON with bounding boxes, and Tagged PDF | 91 out of 100 |
| #4 | agent-reachCLI that gives coding agents read access to login-gated and Chinese web platforms | 89 out of 100 |
| #5 | markitdownPython library and CLI that converts office files, PDFs and audio to Markdown | 87 out of 100 |