Lightweight, self-hosted PDF paper manager with figure extraction, grouping, and tagging. Built with Go + SQLite
-
Updated
Sep 13, 2026 - Go
Lightweight, self-hosted PDF paper manager with figure extraction, grouping, and tagging. Built with Go + SQLite
A NotebookLM-inspired multimodal RAG platform for ingesting, encoding, and reasoning over text, images, and video with traceable, source-grounded generation.
Advanced PDF layout analysis engine for extracting figures, tables, and structured content from complex engineering documents using computer vision and machine learning.
Extract complete, reviewable figures and tables from PDF, arXiv, and HTML papers — an installable AI-agent skill and CLI with contact-sheet QA.
CaptionCrop: Extract figures and tables from research PDFs, with captions, in one command.
End-to-end biomedical paper analysis: VLM figure digitization + NER. Evaluated against HuggingFace VLMs, Ollama, and cloud providers; SotA NER models including GLiNER, DistilBERT, and spaCy.
Codex skill: precise figure+legend capture from paper PDFs to presentations
Convert scientific manuscripts into polished, editable PowerPoint decks with complete evidence coverage and visual QA.
Research Paper Automation Toolkit — Python tools that automate academic workflows: extract figures from PDFs, convert papers to PowerPoint slides, export annotations, generate LaTeX figure blocks, and synchronize PNG/PDF figure formats.
Agent Skill + CLI for extracting complete, publication-quality figures from PDFs without truncating labels, legends, axes, or annotations. High-DPI rendering with safety padding and edge-contact validation.
To associate your repository with the figure-extraction topic, visit your repo's landing page and select "manage topics."