#4949th of 62 in RAG, knowledge and searchFor science, health and research, research and papers
papersgpt-for-zotero
Zotero plugin for chatting with PDFs and searching your whole library
Documentation ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 2.7k
- License
- AGPL-3.0
- Last commit
- Nov 2026
- Last release
- Nov 2026
- Language
- JavaScript
Missed the latest GitHub check; these facts may be older.
Overview
PapersGPT is a Zotero plugin (.xpi) that indexes PDFs locally and answers questions over a single paper, a selection, or the entire library, with click-to-jump citations. It adds Literature Radar for daily digests from arXiv, PubMed and other sources, AutoPilot for batch-reading collections into Zotero Notes, and an MCP server. Models can be 30+ cloud LLMs, built-in local models, Ollama, or any OpenAI-compatible endpoint.
Who it is for: Researchers using Zotero who want local, cited Q&A over their paper library
Strengths
- Parsing, indexing and search run locally; local LLMs work fully offline
- Benchmark: 10,000 PDFs indexed in about 7 minutes, 19.5 ms average query
- Works with Ollama, custom OpenAI-compatible endpoints, or built-in Hugging Face local models
- Exposes the Zotero library to Claude Desktop, Cursor and other clients via MCP
Weaknesses
- Tied to Zotero 7 to 10; unusable outside Zotero
- README points to 'Professional' capabilities on the website, so free versus paid scope is unclear
- Indexing 10,000 PDFs used 2.21 GB RSS and 901 MB of index
- Download links in the README point to different versions (v2.1.0 and v2.2.0)
What it needs
- GPU optional
- Needs Zotero 7+, Ollama (optional)
- Models: OpenAI, Claude, Gemini, DeepSeek, Grok
Also in RAG, knowledge and search
See all 62| Rank | Project | Score |
|---|---|---|
| 1 | RAGFlowRAG engine with deep document parsing, template chunking and agentic retrieval | 90 out of 100 |
| 2 | Open NotebookSelf-hosted NotebookLM alternative for research notebooks, chat, and podcasts | 90 out of 100 |
| 3 | LightRAGGraph-based RAG framework with a REST server and WebUI | 90 out of 100 |
| #4 | deeptutorTutoring workspace with knowledge bases, guided learning, memory and quizzes | 89 out of 100 |
| #5 | MaxKBEnterprise knowledge-base agent platform with RAG, workflows and MCP tools | 89 out of 100 |