What it does
Written by AI from the READMEChats with a paper's PDF, compares several papers and generates a structured review of a selected item, written out as HTML. Optionally links to a paper-curation Python setup for more tools. Needs an API key for Anthropic, OpenAI or Google, or a local Ollama model for summaries and questions. Local review runs on macOS and Linux only.
Reading and comparing many papers is slow. This lets you ask questions of a PDF and produce review write-ups from inside Zotero. Its documentation is mainly in Korean.
What you'll need
Detected automatically- An API keyNeeds a key you get from the service (Anthropic, OpenAI and Google Gemini). What needs it: A key for the chosen AI provider (Anthropic by default; OpenAI or Google if selected) to generate reviews.
- Or: a model on your own computerIt can use a local model such as Ollama
Where your data goes
We found: only contacts services we could identify. 6 addresses in 3 groups.
var GEMINI_BASE_URL = "https://generativelanguage.googleapis.com/v1beta";
const url = field(item, "url") || (doi ? `https://doi.org/${doi}` : "");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.