917Dhj/DeepPaperNote

What it solves

DeepPaperNote addresses the friction of turning academic papers into durable, usable knowledge. It eliminates the repetitive manual work of switching between PDFs, reference managers like Zotero, and note-taking apps, preventing the common problem where reading a paper results in fragmented notes or superficial AI summaries that lack theesprit de corps of the original research.

How it works

It functions as an agent skill (compatible with Claude Code and Codex) that processes one paper at a time. The tool extracts metadata, research questions, methods, evidence, and figures from a PDF (using PyMuPDF) and organizes them into a structured Obsidian note. It can integrate with Zotero to reuse local records and attachments, use the Semantic Scholar API for metadata, and employ OCR for scanned PDFs.

Who it’s for

Researchers, students, and academics who use Obsidian as a personal knowledge base (academic wiki) and want to automate the ingestion of research papers without sacrificing the depth and detail of the analysis.

Highlights

• Evidence-Based Notes: Focuses on preserving formulas, numbers, and figure context rather than providing a simple abstract rewrite.
• Obsidian Integration: Directly generates searchable, linkable pages for an Obsidian vault.
• Zotero Support: Reduces redundant downloads by preferring local Zotero records and attachments.
• Companion Glossary Skill: Includes an optional paper-glossary skill to create reusable terminology notes from paper artifacts.