Upgrade Storage[Plugin] MdBundle for Zotero — Export, analyze & generate PDF/MD pairs for LLM workflows
Hi everyone,
I'd like to share MdBundle for Zotero, a plugin I built to manage the relationship between PDFs and their Markdown equivalents in Zotero. It's currently in beta (v0.9.0) and I'd love feedback from the community.
What it does:
Export matched PDF/MD pairs to a folder (all, PDFs only, or MDs only — matched by filename)
Analyze selected items with a diagnostic report: which items have PDF, MD, both, or neither; flags suspiciously small MDs (<5KB)
Generate MDs from PDFs using Zotero's built-in text extraction (items needing OCR are auto-tagged with needs-ocr)
Select cited items from .docx — reads Zotero citation fields from a Word document and selects all cited items in your library (reports which weren't found)
Why Markdown?
Markdown versions of papers are increasingly useful for AI-assisted research: feeding papers into LLMs (ChatGPT, Claude, etc.), building RAG pipelines, semantic search, or integrating with knowledge tools like Obsidian and Logseq.
Details:
Compatible with Zotero 7, 8, and 9
12 languages: EN, PT-BR, ES, ZH-CN, IT, FR, DE, JA, KO, RU, PL, TR
MIT license
Links:
GitHub: https://github.com/wcmendes/MdBundle-for-Zotero
Download (beta): https://github.com/wcmendes/MdBundle-for-Zotero/releases
I'm actively developing this and would appreciate bug reports, feature suggestions, or translation contributions. Thanks!
I'd like to share MdBundle for Zotero, a plugin I built to manage the relationship between PDFs and their Markdown equivalents in Zotero. It's currently in beta (v0.9.0) and I'd love feedback from the community.
What it does:
Export matched PDF/MD pairs to a folder (all, PDFs only, or MDs only — matched by filename)
Analyze selected items with a diagnostic report: which items have PDF, MD, both, or neither; flags suspiciously small MDs (<5KB)
Generate MDs from PDFs using Zotero's built-in text extraction (items needing OCR are auto-tagged with needs-ocr)
Select cited items from .docx — reads Zotero citation fields from a Word document and selects all cited items in your library (reports which weren't found)
Why Markdown?
Markdown versions of papers are increasingly useful for AI-assisted research: feeding papers into LLMs (ChatGPT, Claude, etc.), building RAG pipelines, semantic search, or integrating with knowledge tools like Obsidian and Logseq.
Details:
Compatible with Zotero 7, 8, and 9
12 languages: EN, PT-BR, ES, ZH-CN, IT, FR, DE, JA, KO, RU, PL, TR
MIT license
Links:
GitHub: https://github.com/wcmendes/MdBundle-for-Zotero
Download (beta): https://github.com/wcmendes/MdBundle-for-Zotero/releases
I'm actively developing this and would appreciate bug reports, feature suggestions, or translation contributions. Thanks!