paper2anything  by QuZhan51496

AI agent for academic paper content generation

Created 1 month ago
288 stars

Top 91.0% on SourcePulse

GitHubView on GitHub
Project Summary

Summary

This repository offers a suite of agent skills designed to automate the transformation of academic papers (PDFs) into various dissemination formats. It targets researchers and academics seeking to efficiently generate presentation slides, conference posters, project webpages, Xiaohongshu posts, and WeChat articles, thereby broadening the reach of their work.

How It Works

The project comprises five distinct, auto-triggerable skills: paper2slides, paper2poster, paper2html, paper2xhs, and paper2wechat. Each skill processes an input PDF, leveraging a pipeline that includes PDF parsing (via MinerU) and specific rendering scripts for each output type. This modular approach allows for independent use and development of each content generation capability.

Quick Start & Requirements

Installation is streamlined via provided shell scripts (tools/install-linux.sh, tools/install-macos.sh) which handle environment setup and dependency linking. Key requirements include:

  • A MINERU_API_TOKEN (obtained separately and configured in .env).
  • System dependencies: poppler-utils, libreoffice, Node.js (>=20.9.0), pptxgenjs, react-icons, react, react-dom, sharp.
  • A Conda environment managed by environment.yml.
  • Project Page: https://quzhan51496.github.io/paper2anything/

Highlighted Details

  • Supports conversion to five diverse output formats: .pptx slides, poster.html/png, index.html project pages, Xiaohongshu posts (JSON/MD), and WeChat articles (MD/HTML).
  • Demonstrates output quality across numerous research domains, including HCI/VR, computer vision, drug discovery, NLP, robotics, and climate simulation.
  • Each skill is designed as an independent, auto-triggerable agent.

Maintenance & Community

The project is developed by the AI4GC Lab at Zhejiang University. Contributors are listed as skill design leads within the lab. No specific community channels (like Discord/Slack) or public roadmaps are detailed in the README.

Licensing & Compatibility

The project is licensed under the Apache 2.0 license. This license is permissive and generally suitable for commercial use and integration into closed-source projects.

Limitations & Caveats

A significant dependency is the MINERU_API_TOKEN, indicating reliance on an external service for core PDF parsing functionality. The installation process requires careful management of several system-level dependencies and specific Node.js versions, which may pose challenges for users unfamiliar with these prerequisites.

Health Check
Last Commit

1 week ago

Responsiveness

Inactive

Pull Requests (30d)
4
Issues (30d)
0
Star History
287 stars in the last 30 days

Explore Similar Projects

Feedback? Help us improve.