What it does
Written by AI from the READMEExtracts bibliographic metadata from PDFs with an LLM and fills in the item's fields. It supports Anthropic, OpenAI and OpenAI-compatible endpoints such as Ollama, sends page images for scanned PDFs, and checks DOIs against CrossRef.
Zotero's own metadata lookup often fails for preprints, theses, scans and foreign-language documents. You review each extracted field side by side before anything is written. Needs an API key unless you use a local model.
What you'll need
Detected automatically- Or: a model on your own computerIt can use a local model such as Ollama
- Zotero 7Not working with Zotero 10
Where your data goes
We found: its code only names services we could identify. 6 addresses in 4 groups.
Forks and copies
No forks listed.
The developer's response
Ratings and reviews
What people who use it say. This is separate from the grade, which is what the code does, and never changes it.
No ratings yet.