arxiv2md converts arXiv HTML pages into clean, well-structured Markdown optimized for LLM consumption. It preserves section headings, math and tables where possible, and offers options to remove references, TOC, and inline citations. The project exposes both a REST API (https://arxiv2md.org) with JSON/markdown endpoints and a CLI (arxiv2md) so agents can fetch either raw markdown or metadata-enriched JSON for downstream tasks like summarization, citation extraction, or content ingestion.
Use arxiv2md when you need readable, machine-friendly versions of arXiv papers for rapid review, LLM summarization, knowledge-base building, or transforming scientific content into blog posts or notes. It is especially useful for agents that must avoid parsing PDFs or that need consistent markdown output.
arxiv2md (pip-installable) for local conversion.This skill is agent-friendly via HTTP (REST) and simple CLI: works with general-purpose code-capable agents and automation runners that can call external HTTP APIs or run Python/CLI tools.
This skill has not been reviewed by our automated audit pipeline yet.
