Document Processing
Extracting and generating PDFs, office files and scans. As of 2026-11-21, 1,405 indexed products match this subcategory (223 with full profiles); 887 were published in the last 90 days, against 279 in the 90 days before, roughly in step with the catalogue as a whole. By GitHub stars, MarkItDown leads, holding 29% of the stars of the 815 products here with their own repository. The most common form is MCP servers (94% of indexed products).
SubcategorySegment label: Crowded DER
Segment statistics
Whole catalogue (all 1,405 indexed products, not only profiled ones). Calculated 2026-11-21.
Crowded. Among the largest fifth of nodes at its level by indexed product count, with launches roughly in step with the catalogue. Size is ranked against the other subcategory nodes; momentum compares this node’s launches in the last 90 days with the 90 before, relative to the whole catalogue’s ratio (score 62 or more = faster, 38 or less = slower; below 5 dated launches it is not measured and the label uses size alone).
Concentration. The Herfindahl–Hirschman index (HHI) adds up each project’s squared share of stars. At 0.118, attention is spread as if across about 8 equally popular projects. Using the common competition-policy thresholds (0.15 and 0.25), that is unconcentrated. Stars measure attention, not usage or quality.
Which product forms serve it
The same need is met by MCP servers, agent skills, plugins, extensions and frameworks. This counts each form across the whole catalogue.
| Product type | Indexed | Share | With a profile |
|---|---|---|---|
| MCP servers | 1,319 | 93.9% | 139 |
| Agent skills | 56 | 4.0% | 56 |
| Plugins | 8 | 0.57% | 8 |
| Libraries | 4 | 0.28% | 4 |
| Infrastructure | 4 | 0.28% | 4 |
| Frameworks | 4 | 0.28% | 4 |
| Agent projects | 4 | 0.28% | 4 |
| Rules packs | 3 | 0.21% | 1 |
| AI APIs | 2 | 0.14% | 2 |
| IDE extensions | 1 | 0.07% | 1 |
3 capabilities
Indexed = whole catalogue; profiled = products with their own page. A product can sit in several, so the rows do not add up to the total.
| Capability | Indexed | Profiled | New, 90 days | Label |
|---|---|---|---|---|
| PDF ProcessingReading, filling, merging and generating PDFs. | 1,068 | 126 | 712 | Crowded |
| OCRRecognizing text in images and scans. | 358 | 72 | 228 | Crowded |
| Office DocumentsWorking with Word, PowerPoint and Excel files. | 262 | 76 | 140 | Crowded |
Top 40 products by GitHub stars
Search the directoryProfiled products only (223 of 1,405), ranked by the stars of their own repository. Products that live in a subfolder of a larger repository (common for skills) show that whole repository's stars and are ranked after them; products without a repository come last. Stars are popularity, not quality or installs.
| # | Product | Type | Publisher | Capabilities | GitHub stars | Last push | Licence | Save and compare |
|---|---|---|---|---|---|---|---|---|
| 1 | MarkItDownPython utility that converts PDF, Office, HTML, images and audio files into Markdown for LLM consumption. | Library | microsoft | 197k | 14d ago | MIT | ||
| 2 | DoclingDocument conversion toolkit that parses PDF, DOCX, PPTX, HTML and images with layout and table understanding into Markdown, JSON or DoclingDocument. | Library | IBM (LF AI & Data) | 71k | today | MIT | ||
| 3 | ai-agent-book《深入理解 AI Agent:设计原理与工程实践》(李博杰 著)开源主仓库:全书正文、编译版 PDF 与按章配套代码 | Agent project | bojieli | 59k | 1mo ago | Apache-2.0 | ||
| 4 | MarkerConverts PDFs, images and Office documents to Markdown, JSON or HTML using deep-learning OCR and layout models, with optional LLM refinement. | Library | Datalab | 41k | 1d ago | Apache-2.0 | ||
| 5 | book-to-skillTurn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work. | Agent skill | virgiliojr94 | 39k | 1d ago | MIT | ||
| 6 | huashu-designHuashu Design 3.4 · 在 agent 里打一句话,拿回能交付的设计:网页 / App 原型 / App Store 宣传图 / 小红书图文 / 可编辑 PPTX / 动画 / 信息图 · 六个候选挑三个方向 · 92 种带样张的风格库 · 该是图的地方放真图 · HTML-native design skill for Claude Code, Codex, Cursor & any agent | Agent skill | alchaincyf | 30k | today | MIT | ||
| 7 | awesome-n8n-templates280+ free n8n automation templates — ready-to-use workflows for Gmail, Telegram, Slack, Discord, WhatsApp, Google Drive, Notion, OpenAI, and more. AI agents, RAG chatbots, email automation, social media, DevOps, and document processing. The largest open-source n8n template collection. | Agent project | enescingoz | 27k | 2mo ago | — | ||
| 8 | rocketride-serverRocketRide is an open source AI meta-harness with the only enterprise-grade runtime built on C++. Build, test and publish durable agents that scale in production. | MCP server | rocketride-org | 20k | today | MIT | ||
| 9 | UnstructuredLibrary and hosted platform for partitioning PDFs, Office files, HTML and images into structured elements and chunks for RAG pipelines. | Library | Unstructured | 16k | 1d ago | Apache-2.0 | ||
| 10 | Skill_SeekersConvert documentation websites, GitHub repositories, and PDFs into Claude AI skills with automatic conflict detection | MCP server | yusufkaraaslan | 15k | 5d ago | MIT | ||
| 11 | Kami👩🚒 Good content deserves good paper. Layout rules and templates that let AI agents export PDF, PNG and editable PowerPoint. | Agent skill | tw93 | 13k | 11d ago | MIT | ||
| 12 | bishengBISHENG is an open-source enterprise Agent platform for building, deploying, and managing AI applications. It combines AI agents, workflows, RAG and knowledge management, desktop agent integration, and vibecoding app hosting with unified model management, evaluation, observability, access control, and enterprise administration. | Infrastructure | dataelement | 12k | 1d ago | Apache-2.0 | ||
| 13 | drawio-skillAgent skill that turns natural language, code, Terraform/K8s, SQL, OpenAPI, AsyncAPI, Protobuf and GraphQL sources into editable, tested draw.io architecture diagrams: incremental sync, multi-view projection, drift diff, CI architecture tests, whiteboard derasterize, interactive HTML/PPTX/Mermaid exports. | MCP server | Agents365-ai | 11k | 11d ago | MIT | ||
| 14 | desktop-commanderMCP server for terminal commands, process management, and file operations across text, code, PDF, DOCX, Excel, images, and structured data. | Plugin | wonderwhy-er | 10k | today | MIT | ||
| 15 | skill收录最全、更新最快的技能Skills商店:精选原创技能包(涵盖文档处理、内容创作、编程开发、机器学习、自动化工作流),全部打包好可直接安装使用!同时自动抓取GitHub上万个Skills项目,按分类、更新时间、Star数量整理。The most comprehensive and frequently updated AI Agent skill library, featuring curated skill packs across document processing, content creation, programming, machine learning, automated workflows, and many more domains. | Agent skill | anbeime | 9.8k | today | — | ||
| 16 | lamdaAndroid Full-Stack Device Control Platform: WebRTC/H.264 remote desktop, UI/OCR/image-matching automation, one-click MITM, built-in Frida, proxy/VPN/frp/P2P networking, MCP/Agent, 160+ APIs, designed for multi-device clusters and engineered deployments. | MCP server | firerpa | 8.8k | 6d ago | MIT | ||
| 17 | codex-ppt-skillGPT-Image-2 PPT Generator Skill for Creating Image-Based PowerPoint Presentations in Codex and Other Skill-Compatible Agents | Agent skill | ningzimu | 8.1k | 5d ago | MIT | ||
| 18 | unstractLLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Workflows | MCP server | Zipstack | 7.5k | 1d ago | AGPL-3.0 | ||
| 19 | PDF CraftConvert scanned PDFs to Markdown or EPUB, and translate PDF and EPUB books via MCP. | MCP server | oomol-lab | 6.8k | 1d ago | MIT | ||
| 20 | SenseNova-SkillsModular SenseNova skills for building AI-powered office assistants and productivity workflows | Agent skill | OpenSenseNova | 6.1k | 8d ago | MIT | ||
| 21 | hermes-agent-orange-bookHermes Agent 从入门到精通 · 橙皮书系列 · Nous Research 开源 AI Agent 框架实战指南 | Framework | alchaincyf | 5.1k | 1mo ago | — | ||
| 22 | modlensThe first vision plugin for DeepSeek Harness, and the vision bridge for every text-only coding agent. Paste an image, get structured JSON evidence (OCR, layout, semantics). | 全网最强 DeepSeek Harness 外挂视觉插件,为 DeepSeek、GLM 等纯文本模型外挂视觉能力,粘贴图片即得结构化 JSON 证据(OCR、版面、语义)。 | Agent skill | liustack | 5.0k | 6d ago | MIT | ||
| 23 | awesome-notebookLM-promptsA curated collection of the strongest NotebookLM slide prompts sourced from the real creative underground . Your go-to resource for AI powerpoint :P | Agent project | serenakeyitan | 4.8k | 5mo ago | MIT | ||
| 24 | Hands-On-AI-EngineeringA curated collection of practical AI projects implementing OCR systems, RAG, AI agents, and other AI use cases. | Agent project | Sumanth077 | 4.1k | 5d ago | — | ||
| 25 | Paper2Poster[NeurIPS 2025] Open-source Multi-agent Poster Generation from Papers | Framework | Paper2Poster | 4.1k | 10d ago | MIT | ||
| 26 | kordocParse Korean documents (HWP, HWPX, PDF, XLSX, DOCX, PPTX) to Markdown; fill forms, diff, render. | MCP server | chrisryugj | 3.1k | today | MIT | ||
| 27 | markdownify-mcpA Model Context Protocol server for converting almost anything to Markdown | MCP server | zcaceres | 3.0k | 16d ago | MIT | ||
| 28 | crosspaste-desktopCross-device clipboard sync for macOS, Windows & Linux — end-to-end encrypted, LAN-only, no cloud. OCR, CLI and MCP server built in. | MCP server | CrossPaste | 2.7k | 2d ago | AGPL-3.0 | ||
| 29 | claude-real-videoLet any LLM watch a video locally — and search everything it has ever watched. | MCP server | HUANGCHIHHUNGLeo | 2.3k | 1d ago | MIT | ||
| 30 | math-modeling-skill数学建模技能 - 面向 CUMCM、MCM/ICM 等数学建模竞赛的三阶段工作流:建模分析、Python/MATLAB 编程与 DOCX 论文生成。包含丰富的算法资源库(优化/预测/评价/图论/机器学习等)、角色指导文档、论文模板和实用工具脚本 | Agent skill | XiaoMaColtAI | 2.0k | today | — | ||
| 31 | academic-pptx-skillA Claude Skill for creating academic presentations (conference talks, seminar slides, thesis defenses, grant briefings). Enforces action titles, structured argument, exhibit discipline, citation standards, and communication-first design. Works alongside Anthropic's built-in PPTX skill. | Agent skill | Gabberflast | 1.6k | 4mo ago | MIT | ||
| 32 | Seal Open DataFrench public open data (data.gouv.fr) cross-referenced by commune, EPCI and department. | MCP server | sealopendata.fr | 1.6k | 1d ago | MIT | ||
| 33 | gpt-image2-ppt-skillsClone any .pptx into your own deck — OpenAI gpt-image-2 mimics the layout, you supply the content. 10 bundled styles. | 把任何 .pptx 模板"抄"成你的 PPT:gpt-image-2 仿版式、你换内容,另含 10 套精选风格。Claude Code / OpenClaw skill. | Agent skill | JuneYaooo | 1.5k | 3mo ago | Apache-2.0 | ||
| 34 | deepseek-harness-orange-bookDeepSeek Harness橙皮书《从开机到拆开》:完整系统提示词、129行启动清单、三份原始会话日志——官方文档没有的一手实测。PDF/EPUB/HTML免费下载 | Framework | alchaincyf | 1.4k | 1mo ago | — | ||
| 35 | agent-vision-toolkit为纯文本模型"看图“设计更好的视觉工具箱和技能,支持多图理解,图片问答,前端UI还原、GUI 自动化等,并可选无缝接入多个主流agent,直接识别粘贴图片| A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and GUI automation, with optional seamless integration for Codex, Claude Code, Pi, Oh My Pi, and OpenCode | Agent skill | Anionex | 1.3k | 1mo ago | MIT | ||
| 36 | MakeMoneyWithAIA list of open-source AI projects you can use to generate income easily. | MCP server | garylab | 1.2k | today | — | ||
| 37 | WinShunWin顺:免费开源的 Windows 快速搜索启动器。双击 Ctrl,拼音秒搜文件、全文搜索 Word/Excel/PDF、剪贴板历史(代替 Win+V)、对话框搜索、任务栏搜索、插件、AI 助手 MCP。Free Windows search launcher: pinyin file search, full-text search, clipboard history, MCP server. Everything/Listary alternative. | MCP server | LingCore | 1.1k | today | MIT | ||
| 38 | anymdAny file → clean Markdown for AI agents: PDF, Office, EPUB, HTML, images, audio/video. Local MCP. | MCP server | SylphxAI | 1.1k | today | MIT | ||
| 39 | CitraCitra — PDF answers with page-level proof: structure, tables, OCR, and page citations. | MCP server | SylphxAI | 1.1k | today | MIT | ||
| 40 | PDF Reader MCPEvidence-first PDF MCP. Agent Document Twin with citeable page+bbox evidence. | MCP server | SylphxAI | 1.1k | today | MIT |
Most common integrations
Third-party services named by products in this node, whole catalogue.
| Integration | Products | Share |
|---|---|---|
| Microsoft Excel | 36 | 2.6% |
| YouTube | 16 | 1.1% |
| QuickBooks | 7 | 0.5% |
| GitHub | 5 | 0.4% |
| Stripe | 5 | 0.4% |
| 4 | 0.3% | |
| Android | 3 | 0.2% |
| Azure | 3 | 0.2% |
| Google Docs | 3 | 0.2% |
| Notion | 3 | 0.2% |
| Xero | 3 | 0.2% |
| AWS | 2 | 0.1% |
| Discord | 2 | 0.1% |
| Gmail | 2 | 0.1% |
| Google Ads | 2 | 0.1% |
Launches per month
New Document Processing products per monthSRC
Whole catalogue, by publication month, 2024-12 to 2026-11. The last month is partial; undated products are excluded.
Show the data as a table
| Products published (products) | |
|---|---|
| 2024-12 | 1 |
| 2025-02 | 1 |
| 2025-03 | 3 |
| 2025-05 | 3 |
| 2025-08 | 1 |
| 2025-09 | 5 |
| 2025-10 | 10 |
| 2025-12 | 7 |
| 2026-01 | 5 |
| 2026-02 | 29 |
| 2026-03 | 29 |
| 2026-04 | 60 |
| 2026-05 | 45 |
| 2026-06 | 59 |
| 2026-07 | 106 |
| 2026-08 | 141 |
| 2026-09 | 189 |
| 2026-10 | 378 |
| 2026-11 | 282 |
Related opportunities
Opportunity radarScored gaps for this node or anything beneath it. Scores rank hypotheses; they do not predict demand.
No scored opportunity here
Capability gaps are only scored inside subcategories with at least 20 indexed products, and only the top 80 are kept. None falls under this node.
Limits of these numbers
- Products are placed here by whole-word keyword rules on their name, description and repository topics, and inherit every ancestor of a matched node. Products that do this without naming it are missed; ambiguous words cause false matches. Methodology
- About half of the catalogue matches no node at all, so absolute counts understate every category.
- Launch counts use the publication date each source reports; for auto-discovered repositories that is the repository’s creation date.
- Stars and concentration cover only products with their own repository (not a subfolder of a larger one). They measure attention, not adoption.
Page data last updated .