PulseAugur
EN
LIVE 22:54:17

New kordoc library converts Korean HWP documents to Markdown for AI

By PulseAugur Editorial · [1 sources] ·

A new open-source library called kordoc has been developed to convert Korean HWP documents into Markdown and structured data, addressing a significant challenge for AI and RAG pipelines. The library, built with TypeScript and released under the MIT license, can parse various HWP formats, including HWP 3.x/5.x, HWPX, and HWPML, as well as other document types like PDF, XLS/XLSX, and DOCX. Kordoc also offers features such as diffing, form filling, PII masking, and can be integrated with AI agents via an MCP server or as a plugin for tools like Claude Code. AI

IMPACT Enables AI models to process previously inaccessible Korean government documents, potentially improving data analysis and automation in public services.

RANK_REASON New open-source library release for document conversion.

Read on dev.to — MCP tag →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

New kordoc library converts Korean HWP documents to Markdown for AI

How we ranked this

Signal score
1 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
New open-source library release for document conversion.
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
product, infra
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
1 days old
Coverage has settled into its steady-state source set.

Full methodology in our editorial standards.

COVERAGE [1]

  1. dev.to — MCP tag TIER_1 English(EN) · Chris Ryu ·

    Parsing Korea's HWP government documents into Markdown for LLMs

    <p>I am a local civil servant at the Gwangjin-gu District Office in Seoul. I spent seven years wrestling HWP files at work, and when I started wiring LLMs into that work, the files were the first wall I hit. Almost everything I read and write on the job is an HWP or HWPX document…

RELATED ENTITIES

RELATED TOPICS