657 projects whose own agent configuration covers documents. These are not mods to install — they are how the maintainers of these repositories tell an agent what to do, and what to avoid.
All projects Building agents7,412Data and AI4,299Backend and APIs3,694Languages3,682Planning3,492Git and workflow3,285Code review2,942Memory and context2,581Research2,499Writing and docs2,458Testing2,454Frontend2,420
Any agent Claude CodeCodexOpenCodeGitHub CopilotGemini CLICursorKiroWindsurf
| Project | Stars | Configures | Files | Always loaded |
|---|---|---|---|---|
| Stirling-Tools/Stirling-PDF stirling.com #1 PDF Application on GitHub that lets you edit PDFs on any device anywhere | 91,359 | Claude Code | 2 | — |
| Fission-AI/OpenSpec openspec.dev Spec-driven development (SDD) for AI coding assistants. | 67,407 | Claude Code, Codex, OpenCode | 5 | — |
| hugohe3/ppt-master hugohe3.github.io AI turns documents or topics into real, native PowerPoint decks—with native shapes, transi | 52,260 | Claude Code, Codex, OpenCode | 2 | 2,634 tok |
| CherryHQ/cherry-studio cherryai.com AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified ac | 51,494 | Claude Code, Codex, OpenCode | 2 | 4,719 tok |
| HKUDS/LightRAG arxiv.org [EMNLP2025] LightRAG: Simple and Fast Retrieval-Augmented Generation | 39,427 | Claude Code, Codex, OpenCode | 4 | 5,707 tok |
| virgiliojr94/book-to-skill Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use | 28,707 | Claude Code, Codex, OpenCode | 2 | 1,099 tok |
| alshedivat/al-folio alshedivat.github.io A beautiful, simple, clean, and responsive Jekyll theme for academics | 16,091 | Claude Code, Codex, GitHub Copilot, OpenCode | 12 | 3,826 tok |
| run-llama/liteparse developers.llamaindex.ai A fast, helpful, and open-source document parser | 12,256 | Claude Code, Codex, OpenCode | 2 | 2,104 tok |
| tw93/Kami kami.tw93.fun 👩🚒 Good content deserves good paper. | 11,218 | Claude Code, Codex, OpenCode | 2 | 6,917 tok |
| StarTrail-org/PixelRAG arxiv.org https://arxiv.org/abs/2606.28344. The end of web parsing. The beginning of scalable pixel- | 9,884 | Claude Code | 1 | 371 tok |
| openclaw/gogcli gogcli.sh Google Workspace in your terminal. | 8,368 | Claude Code, Codex, OpenCode | 33 | 754 tok |
| jgraph/drawio-mcp | 5,348 | Claude Code | 1 | 3,005 tok |
| nyblnet/bento bento.page Bento, the office suite that fits in a file | 4,821 | Claude Code, Codex, OpenCode | 2 | 14,784 tok |
| intuitem/ciso-assistant-community intuitem.com CISO Assistant is a one-stop-shop GRC platform for Risk Management, AppSec, Compliance & A | 4,410 | Claude Code | 5 | — |
| dathere/qsv qsv.dathere.com Blazing-fast Data-Wrangling toolkit | 3,776 | Claude Code, GitHub Copilot, Gemini CLI | 6 | 2,297 tok |
| SamurAIGPT/llm-wiki-agent A personal knowledge base that builds and maintains itself. Drop in sources — Claude (or C | 3,491 | Claude Code, Codex, Gemini CLI, OpenCode | 7 | 5,977 tok |
| huangwb8/ChineseResearchLaTeX A collection of commonly used LaTeX templates for Chinese research | 2,700 | Claude Code, Codex, OpenCode | 2 | 11,923 tok |
| K-Dense-AI/claude-scientific-writer k-dense.ai A general purpose scientific writer | 2,305 | Claude Code, Codex, OpenCode | 28 | 10,828 tok |
| OpenCoworkAI/open-cowork Open-source AI agent desktop app for Windows & macOS. One-click install Claude Code, MCP t | 2,109 | Claude Code | 5 | — |
| ranuts/document edit.chaxus.com Edit DOCX/XLSX/PPTX in your browser — client-side, no server, works offline (OnlyOffice + | 1,924 | Claude Code | 1 | 23,895 tok |
| chrisryugj/kordoc npmjs.com Parse everything — HWP, HWPX, PDF, and Office documents into Markdown. CLI and MCP server | 1,792 | Claude Code | 2 | 5,610 tok |
| deusyu/translate-book Agent skill for Codex, Claude Code, and OpenClaw that translates entire books (PDF/DOCX/EP | 1,575 | Claude Code, Codex, OpenCode | 2 | 1,875 tok |
| Open-Source-Legal/OpenContracts open-source-legal.github.io The open document intelligence platform for builders and hackers - DMS for the agentic wor | 1,466 | Claude Code | 1 | 9,286 tok |
| daaain/claude-code-log daaain.github.io A Python CLI tool that converts Claude Code transcript JSONL files into readable HTML / Ma | 1,209 | Claude Code | 6 | 1,376 tok |
| sunchaokun/PPT-Design-Skill sunchaokun.github.io Precision PPT design skill for OpenCode/Claude Code/Codex, with 40,000+ styles, pixel-perf | 1,195 | Claude Code, Codex, OpenCode | 2 | 581 tok |
| galkahana/PDF-Writer pdfhummus.com High performance library for creating, modiyfing and parsing PDF files in C++ | 1,022 | Claude Code, GitHub Copilot | 3 | 2,896 tok |
| negokaz/excel-mcp-server A Model Context Protocol (MCP) server that reads and writes MS Excel data | 1,021 | Claude Code | 1 | 827 tok |
| piratuks/invoice-builder Invoice and quotation builder desktop app with PDF export, designed for small businesses a | 978 | Claude Code, Codex, GitHub Copilot, OpenCode | 7 | 2,558 tok |
| huifer/WellAlly-health wellally.tech Ally-Health is an intelligent healthcare assistant that harnesses advanced AI technology a | 939 | Claude Code | 77 | — |
| JaguarJack/catch-admin catchadmin.com CatchAdmin is a powerful, extensible modern PHP administration system. It uses a frontend- | 930 | Claude Code, Codex, OpenCode | 11 | 1,778 tok |
| yorkie-team/yorkie yorkie.dev Document Store for collaborative applications | 927 | Claude Code | 1 | 1,039 tok |
| irsdl/webhacklist irsdl.github.io Archive of the Top 10 Web Hacking Techniques - every nominee since 2006, preserved | 808 | Claude Code, Codex | 15 | 1,363 tok |
| magicyuan876/mineru-tianshu mineru-tianshu.vercel.app Tianshu - An enterprise-grade all-in-one AI data preprocessing platform | PDF/Office to Ma | 783 | Claude Code | 1 | 2,072 tok |
| yukiyokotani/office-open-xml-viewer ooxml.silurus.dev A browser-based viewer for Office Open XML documents that renders to an HTML Canvas elemen | 779 | Claude Code, Codex, OpenCode | 3 | 4,609 tok |
| ConardLi/rag-skill A Skill dedicated to local knowledge base retrieval | 711 | Claude Code, Codex | 2 | — |
| jason-effi-lab/karpathy-llm-wiki-vault | 701 | Claude Code | 4 | 1,191 tok |
| agarwalvishal/claude-chat-exporter agarwalvishal.github.io One-click, privacy-first exporter for Claude.ai chats — clean Markdown with artifacts and | 670 | Claude Code | 2 | 4,543 tok |
| Doryoku1223/lunwen-skill One-click thesis first-draft Skill for undergraduate computer science students, supporting | 644 | Claude Code | 2 | — |
| opendatalab/MinerU-Document-Explorer Agent-native knowledge engine with MCP tools for document indexing, wiki organization, fas | 631 | Claude Code | 1 | 3,838 tok |
| iBigQiang/feedgrab Universal content grabber — fetch, normalize, and digest content from 7+ platforms (WeChat | 606 | Claude Code, Codex, OpenCode | 4 | 24,899 tok |
| ggozad/haiku.rag ggozad.github.io Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and mul | 592 | Claude Code | 2 | — |
| vivekVells/mcp-pandoc pypi.org MCP server for document format conversion using pandoc. | 579 | Claude Code, Codex, OpenCode | 2 | 7,051 tok |
| 7toCR/paper2patent 📄→💡 Paper2Patent: An intelligent paper-to-patent template library for translating resear | 573 | Claude Code, Codex, GitHub Copilot, Gemini CLI | 4 | 601 tok |
| ZimoLiao/scholaraio zimoliao.github.io Scholar All-In-One: A research infrastructure for AI agents | 569 | Claude Code, Codex, GitHub Copilot, Cursor, OpenCode | 51 | 2,598 tok |
| neiltron/apple-health-mcp Local-first Apple Health MCP server. Lets AI assistants answer questions about your sleep, | 564 | Claude Code, Codex, OpenCode | 2 | 571 tok |
| run-llama/ParseBench arxiv.org ParseBench - A Document Parsing Benchmark for AI Agents | 563 | Claude Code | 1 | — |
| Superagentsys/novalclaw novalclaw is next generation AI format | 562 | Claude Code, Codex | 1 | — |
| liliu-z/stashbase stashbase.ai Turn local files into searchable context for AI agents. | 559 | Claude Code, Codex, OpenCode | 2 | 1,898 tok |
| criptogus/HermesOffice AI-native office suite (Docs, Sheets, Slides, PDF) where the Hermes Agent is the brain — o | 547 | Claude Code | 1 | 627 tok |
| thiswillbeyourgithub/wdoc wdoc.readthedocs.io Summarize and query from a lot of heterogeneous documents. Any LLM provider, any filetype, | 541 | Claude Code | 1 | 2,156 tok |