html-to-markdown
High performance and CommonMark compliant HTML to Markdown converter. Maintained by the Kreuzberg team. Kreuzberg is a fast, polyglot document intelligence engine with a Rust core. It extracts structured data from 98+ document formats using streaming parsers and built-in OCR.
The html-to-markdown Claude Code plugin enables AI coding assistants to convert HTML documents into clean Markdown or Djot format. Built on a high-performance Rust core, it handles real-world HTML including malformed markup, unclosed tags, and mixed encodings without data loss. The plugin extracts structured metadata (Open Graph, JSON-LD, Twitter cards) and converts tables to GitHub-flavored Markdown in a single operation. It provides AI agents with reliable HTML-to-Markdown conversion capabilities across 16 programming languages through a unified API.
Key Features
Use Cases
- 01Converting scraped web pages to Markdown for AI context windows and RAG pipelines
- 02Extracting clean content from documentation sites and technical articles
- 03Batch processing HTML archives into Markdown for search indexing or analysis
- 04Parsing structured metadata from web pages for knowledge graphs
- 05Converting email HTML or rich-text content to plain Markdown
- 06Preprocessing web content for LLM training or fine-tuning datasets
Related Plugins
View moreandrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
claude-mem
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Understand-Anything
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
rtk
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
html-to-markdown — FAQ
What is the html-to-markdown Claude Code plugin?+
It's a Claude Code plugin that provides AI coding assistants with high-performance HTML-to-Markdown conversion capabilities. The plugin uses a Rust core to handle real-world HTML including malformed markup and extracts structured metadata in the same pass.
How do I install the html-to-markdown plugin in Claude Code?+
Run '/plugin marketplace add xberg-io/html-to-markdown' to add the repository, then '/plugin install html-to-markdown@html-to-markdown' to install the plugin.
Which AI coding assistants support this plugin?+
The plugin works with Claude Code, Codex CLI, Cursor, Gemini CLI, Factory Droid, GitHub Copilot CLI, and opencode. Installation commands vary by client but all reference the xberg-io/html-to-markdown repository.
Does the html-to-markdown plugin require API keys?+
No API keys are required. The plugin runs locally and performs all conversions using the built-in Rust engine without external service calls.
Is the html-to-markdown plugin free to use?+
Yes, it is released under the MIT License and is completely free and open source.
Can the plugin handle broken or malformed HTML?+
Yes, it's specifically designed to process real-world HTML with unclosed tags, CDATA, custom elements, broken entities, nested tables, and mixed encodings without losing content.
How do I install html-to-markdown?+
Open the source repository on GitHub and follow its README. html-to-markdown is a plugin — MCP Agents Market links you directly to the official repo.
Is html-to-markdown free?+
html-to-markdown is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.