Resophy
๐ฏ Read research papers faster with AI. Resophy is an HTML-based AI paper reader with: ๐ค AI Translation & Analysis โ instantly understand structure, contributions, and results ๐ Daily arXiv Recommendations โ discover relevant papers with less noise ๐ ๏ธ Vibe Coding Oriented โ agent-friendly and easy to customize
Install / Use
/learn @Mountchicken/ResophyREADME
English | ็ฎไฝไธญๆ | Installation Guide
<span style="color:rgb(154, 46, 222);">All Resophy code is built using Cursor (Sonnet 4.5/Auto) generation with manual verification</span>
</div>Resophy
๐ News
2025-12-27๏ผMinerU Official API Support: Resophy now supports MinerU's official cloud API! You can use MinerU's cloud service for PDF parsing without deploying your own MinerU server. Simply configure your API token in Settings โ Agentic โ MinerU Mode (select "Cloud API") and enter your token from https://mineru.net/. This makes it easier to get started with AI interpretation features without GPU requirements.
In this era of information explosion, researchers often feel overwhelmed when facing massive amounts of papers. How to quickly extract the essence and understand cutting-edge achievements has become a pain point for every researcher. Resophy was born with the intention of helping you bid farewell to inefficient paper reading, empowering researchers, and making paper reading more efficient and intelligent ๐โก.
Resophy is a fully open-source, Vibe Coding-oriented modern paper reader that helps you quickly understand the core content of papers through a simple tech stack (HTML + JavaScript + Python Flask) and AI features ๐ค๐ก. From automatic translation to paper parsing, from intelligent recommendations to one-click Zotero import, Resophy provides a one-stop solution for your paper reading needs ๐โจ. Most importantly, you can customize features at any time through Vibe Coding, creating a paper assistant tailored to you ๐จ๐ ๏ธ.
๐ Core Features
<div align="center" xmlns="http://www.w3.org/1999/html"> <!-- logo --> <p align="center"> <img src="https://github.com/user-attachments/assets/5fbe6d8f-570a-491d-9c54-1c008b23399d" style="vertical-align:middle;"> </p> </div>Table of Contents
- Resophy - Core Features
1. Installation
<div align=center> <img src="https://github.com/user-attachments/assets/73d25cfa-5791-4b54-a131-d816f51afebb"> <div style="margin-top:8px; color: #555; font-size: 16px;"> Resophy adopts a frontend-backend separated architecture </div> </div>- Main Service (Resophy Core): HTML + JavaScript + Python Flask backend service, providing core features such as paper management, classification, and search
- AI Services include:
- LLM Server: LLM inference service for AI translation, interpretation, and arXiv paper analysis (optional, supports local deployment or remote API)
- MinerU Server: Document parsing service for PDF to Markdown parsing (optional, for AI features)
Resophy uses uv for dependency management and supports separated deployment architecture. You can deploy Resophy main service and AI servers on different machines. For installation and configuration instructions, please refer to:
2. Quick Start
In this section, we briefly introduce some usage methods of Resophy
2.1 โ๏ธ First Step: Initial Configuration
<div align=center> <img src="https://github.com/user-attachments/assets/6cc2292a-d3df-45d2-8bda-15f9edd13189"> <div style="margin-top:8px; color: #555; font-size: 16px;"> First step: configure parameters and migrate papers from Zotero </div> </div> <div align="center">| Configuration Module | Location | Main Features | Usage | |---------|------|---------|---------| | ๐ธ User Settings | Settings Interface โ "User" Tab | โข Avatar upload<br>โข Username setting<br>โข Reading heatmap color theme<br>โข Recent reading records | 1. Click avatar in top right corner<br>2. Enter "User" tab<br>3. Upload avatar, set username, select color<br>4. Auto-save settings | | ๐ค Agentic Settings | Settings Interface โ "Agentic" Tab | โข LLM API configuration (model name, URL, key)<br>โข MinerU server configuration<br>โข AI interpretation prompt customization | 1. Enter "Agentic" tab<br>2. Configure LLM API and MinerU address<br>3. (Optional) Customize prompts<br>4. Test connection and save | | ๐ฐ Daily arXiv | Settings Interface โ "Daily arXiv" Tab | โข arXiv category configuration (cs.CV, cs.AI, etc.)<br>โข Crawling settings (retention days, check interval)<br>โข Keyword list (for intelligent classification)<br>โข Institution configuration | 1. Enter "Daily arXiv" tab<br>2. Add arXiv categories<br>3. Configure crawling parameters and keywords<br>4. (Optional) Add custom institutions<br>5. Save settings | | ๐ฅ Zotero Import | Settings Interface โ "Import" Tab | โข Target directory selection<br>โข RDF file drag-and-drop upload<br>โข Import progress display<br>โข Import result statistics | 1. Export from Zotero as RDF format<br>2. Enter "Import" tab<br>3. (Optional) Select target directory<br>4. Drag and drop RDF file<br>5. View import progress and results |
</div> <details open> <summary><strong>Expand for Detailed Introduction</strong></summary>๐ธ User Settings
Feature Details:
- Avatar Upload: Click avatar area to upload custom avatar, supports preview and cropping
- Username Setting: Enter username (default: Paper Reader)
- Reading Heatmap Color: Select color theme (green/blue/rose pink) for visualizing daily reading time
- Recent Reading Records: Display list of recently read papers for quick access to history
๐ค Agentic Settings (AI Feature Configuration)
Feature Details:
- LLM API Configuration:
- Model Name: Enter model name (e.g.,
Qwen3-4B-Instruct-2507) - Base URL: Enter API address (local:
http://0.0.0.0:6002/v1or remote API) - API Key: Enter access key
- Test Button: Verify API connection
- Model Name: Enter model name (e.g.,
- MinerU Configuration:
- Mode Selection: Choose between "Local Deployment" or "Cloud API"
- Local Deployment: Enter server address (e.g.,
http://0.0.0.0:6001) for self-hosted MinerU server - Cloud API: Enter API token from https://mineru.net/ for MinerU cloud service
- Test Button: Verify connection (server or API token)
- AI Interpretation Prompt: Large text editor for customizing System Prompt, controlling AI interpretation generation style
Purpose: Unified AI feature configuration for translation, interpretation, Daily arXiv, and all other AI features
๐ฐ Daily arXiv Settings
Feature Details:
- arXiv Category Configuration: Add/delete category tags (cs.CV, cs.AI, etc.), provides quick buttons for common categories
- Crawling Settings: Paper retention days (1-30 days), check interval (5-60 minutes)
- Keyword List: Add keyword tags, set maximum number of keywords (1-3), for AI automatic classification
- Institution Configuration: Add custom institutions, supports editing abbreviations and full name variants
๐ฅ Import from Zotero
Feature Details:
- Target Directory Selection: Dropdown menu to select import location (optional, default root directory)
- File Upload Area
Related Skills
proje
Interactive vocabulary learning platform with smart flashcards and spaced repetition for effective language acquisition.
YC-Killer
2.7kA library of enterprise-grade AI agents designed to democratize artificial intelligence and provide free, open-source alternatives to overvalued Y Combinator startups. If you are excited about democratizing AI access & AI agents, please star โญ๏ธ this repository and use the link in the readme to join our open source AI research team.
best-practices-researcher
The most comprehensive Claude Code skills registry | Web Search: https://skills-registry-web.vercel.app
groundhog
400Groundhog's primary purpose is to teach people how Cursor and all these other coding agents work under the hood. If you understand how these coding assistants work from first principles, then you can drive these tools harder (or perhaps make your own!).
