ZotLLM
A Windows companion for Zotero that indexes your PDFs with page numbers intact and answers questions with per-page citations — written by Claude.
Project intro
ZotLLM is a Windows desktop application that works alongside Zotero for researchers who want answers grounded in their own literature. You organise work into projects, each with its own knowledge corpora — a corpus is a selection of Zotero collections or whole libraries, group libraries included. ZotLLM reads the PDFs, Word documents and other texts, keeps their page numbers, and indexes everything locally on your computer.
On top of the index it offers semantic search, an Ask mode that answers questions with citations down to the page (a click opens the PDF at the cited page), and literature reviews drawn only from the texts in the project. Models can be reached through Claude, ChatGPT, Gemini or DeepSeek APIs, or locally via Ollama. Exported citations land as real Zotero fields in Word, LaTeX and Markdown.
The author is explicit about how it was made. From the README's "#vibe-coded" section: "Vibe-coded. ZotLLM was written by Claude (Anthropic's AI model, working in Claude Code) – the application, the Zotero plugin, the installer scripts, the tests and the documentation. The project's initiator, avibecoder, defined what to build, tested every version in day-to-day research and decided on each next step; no code was written by hand." It ships with roughly 200 automated tests and a prominent "use it as a tool, not as a replacement for your own scholarly work" note — verify critically, read the sources. 12 stars on GitHub, MIT, actively pushed (2026-10-23). Windows only; there is no web demo, so the demo link points at the repository.
Actions
Tech stack
Project info
- Project category
- Office
- Project status
- Online
- Collaboration intent
- None