OCR
Recognizing text in images and scans. As of 2026-11-21, 358 indexed products offer it (72 with full profiles), in 7 forms: 342 MCP servers, 7 Agent skills, 2 AI APIs, 2 Infrastructure. 228 were published in the last 90 days, against 77 in the 90 days before. Marker has the most GitHub stars, 29% of the total across 232 products with their own repository.
CapabilitySegment label: Crowded DER
Available as
All in the directoryProfiled products grouped by product form. Within each form: own-repository products by GitHub stars, then products in a subfolder of a larger repository (they show that repository's stars), up to 10 each.
MCP servers 342 indexed · 56 profiled
Protocol-level reach: 36 of the 45 active platforms AgentSidekick tracks document support for MCP. DER Which platforms
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | Skill_SeekersConvert documentation websites, GitHub repositories, and PDFs into Claude AI skills with automatic conflict detection | yusufkaraaslan | 15k | 5d ago | ||
| 2 | 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. | firerpa | 8.8k | 6d ago | ||
| 3 | unstractLLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Workflows | Zipstack | 7.5k | 1d ago | ||
| 4 | PDF CraftConvert scanned PDFs to Markdown or EPUB, and translate PDF and EPUB books via MCP. | oomol-lab | 6.8k | 1d ago | ||
| 5 | kordocParse Korean documents (HWP, HWPX, PDF, XLSX, DOCX, PPTX) to Markdown; fill forms, diff, render. | chrisryugj | 3.1k | today | ||
| 6 | markdownify-mcpA Model Context Protocol server for converting almost anything to Markdown | zcaceres | 3.0k | 16d ago | ||
| 7 | crosspaste-desktopCross-device clipboard sync for macOS, Windows & Linux — end-to-end encrypted, LAN-only, no cloud. OCR, CLI and MCP server built in. | CrossPaste | 2.7k | 2d ago | ||
| 8 | claude-real-videoLet any LLM watch a video locally — and search everything it has ever watched. | HUANGCHIHHUNGLeo | 2.3k | 1d ago | ||
| 9 | MakeMoneyWithAIA list of open-source AI projects you can use to generate income easily. | garylab | 1.2k | today | ||
| 10 | 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. | LingCore | 1.1k | today |
Agent skills 7 indexed · 7 profiled
Protocol-level reach: 26 of the 45 active platforms AgentSidekick tracks document support for the Agent Skills format. DER Which platforms
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | 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)。 | liustack | 5.0k | 6d ago | ||
| 2 | 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 | Anionex | 1.3k | 1mo ago | ||
| 3 | dsh-vision-toolkit[dsh]为纯文本模型设计更强大的视觉工具箱:一行安装使用、粘贴图片直接识别、多张图片问答、截图到前端UI 还原等|DeepSeek Harness-native integration for agent-vision-toolkit: image Q&A, long-screenshot OCR, UI restoration, grounding, pixel diff, Artifacts, and Web UI. | Anionex | 949 | today | ||
| 4 | pdfUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. | anthropics | — | 5d ago | ||
| 5 | open-code-review-delegateReview workspace changes, PRs, commits, or branch comparisons with the host agent's model. OCR's CLI handles file selection and rule resolution; this skill defines the review workflow, coverage requirements, and output format. Use when the user has no separate API key for OCR or wants to reuse their coding-agent subscription or model setup. For OCR's full native pipeline with its own model provider, choose open-code-review instead. | alibaba | — | today | ||
| 6 | pdfUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill. | eigent-ai | — | 1d ago | ||
| 7 | nature-paper2wordCompile an academic Markdown manuscript into a journal- or school-compliant Word (.docx): declared typography, native OMML equations, three-line tables, cross-references, per-section page numbers, CSL bibliographies (GB/T 7714, APA, Nature, IEEE), and pre/post-export quality gates. 把学术论文的 Markdown 稿件导出为符合期刊或学位论文规范的 Word:摘要、公式编号、三线表、题注、交叉引用、目录域、参考文献。Use when the user wants a submission-ready .docx — 论文转 Word、学位论文排版、期刊投稿排版、prepare submission docx — or a readable copy of a manuscript. Not for PDF, HTML or LaTeX output, and not for slide decks or grant forms. Also use for reference-paper reformatting and format requirements supplied as PDF, Word, images or pasted text, with automatic image-text recognition. 参考论文样式提取、按参考文档重排版、期刊排版要求、图片与扫描件识别。 | Yuan1z0825 | — | 1d ago |
AI APIs 2 indexed · 2 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | Mistral AI APIAPI for Mistral open-weight and proprietary models plus OCR, embeddings and an Agents API with connectors. | Mistral AI | 777 | 2d ago | ||
| 2 | LlamaParseHosted document parsing API that uses vision and language models to convert complex PDFs, slides and spreadsheets into Markdown or JSON. | LlamaIndex | 68 | today |
Infrastructure 2 indexed · 2 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | 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. | dataelement | 12k | 1d ago | ||
| 2 | VectorHubDeprecated historical repo. Superlinked now develops SIE, a self-hosted inference engine for embeddings, reranking, OCR, extraction, and document processing. | superlinked | 535 | 5d ago |
Libraries 2 indexed · 2 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | MarkerConverts PDFs, images and Office documents to Markdown, JSON or HTML using deep-learning OCR and layout models, with optional LLM refinement. | Datalab | 41k | 1d ago | ||
| 2 | UnstructuredLibrary and hosted platform for partitioning PDFs, Office files, HTML and images into structured elements and chunks for RAG pipelines. | Unstructured | 16k | 1d ago |
Plugins 2 indexed · 2 profiled
2 of these are Claude plugins, which Claude Code documents (protocol-level). DER
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | offline-game-revival🎮 AI agent skill that revives shut-down mobile games as fully offline memorial builds — plus a zero-token pipeline that rescues lost game data from screenshots & screen recordings. 停服手游离线化 · 录屏抽帧OCR | Cynthia-wlan9509 | 111 | 5d ago | ||
| 2 | vision-specialistExpert in vision models, OCR systems, barcode detection, and visual AI. Stays current with latest models (GPT-4V, Claude Vision, Mistral-OCR, etc.), optimization techniques, and specialized libraries. Use PROACTIVELY for image processing, document analysis, or visual AI tasks. | ccplugins | — | 3mo ago |
Agent projects 1 indexed · 1 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | Hands-On-AI-EngineeringA curated collection of practical AI projects implementing OCR systems, RAG, AI agents, and other AI use cases. | Sumanth077 | 4.1k | 5d ago |
Which platforms these forms can reach
All platformsProtocol-level: the platform documents support for the standard. No specific pairing has been tested.
MCP servers 342 indexed here
36 platforms document MCP support CUR.
ContinueOpenCodeClaude CodeCodexGemini CLIZedOpenHandsClineWarpgooseQwen CodeBolt (bolt.new)KiroAmazon Bedrock AgentCoreAmpApps in ChatGPT / Apps SDK (now ChatGPT Plugins)Augment CodeChatGPTClaude (claude.ai apps)Claude DesktopCursorDevinDevin Desktop (formerly Windsurf)Factory (Droid)Gemini (app)Gemini Enterprise Agent Platform (formerly Vertex AI / Vertex AI Agent Builder)GitHub CopilotGitHub Copilot cloud agent (formerly Copilot coding agent)Google AntigravityJetBrains AI AssistantJunieLovableMicrosoft Copilot StudioReplit AgentTabninev0
Agent skills 7 indexed here
26 platforms document Agent Skills support CUR.
OpenClawOpenCodeClaude CodeCodexGemini CLIOpenHandsWarpgooseBolt (bolt.new)KiroAmpApps in ChatGPT / Apps SDK (now ChatGPT Plugins)ChatGPTClaude (claude.ai apps)Claude DesktopCursorDevinDevin Desktop (formerly Windsurf)Factory (Droid)Gemini (app)GitHub CopilotGitHub Copilot cloud agent (formerly Copilot coding agent)Google AntigravityJunieReplit AgentTabnine
Platforms publishers name
| Platform | Profiled products naming it |
|---|---|
| Claude Code | 2 |
| Codex | 1 |
| OpenCode | 1 |
Integrations most often paired
Third-party services named by products with this capability, whole catalogue.
| Integration | Products | Share |
|---|---|---|
| YouTube | 5 | 1.4% |
| Android | 3 | 0.8% |
| Microsoft Excel | 3 | 0.8% |
| QuickBooks | 3 | 0.8% |
| GitHub | 2 | 0.6% |
| Xcode / iOS | 2 | 0.6% |
| AWS | 1 | 0.3% |
| Azure | 1 | 0.3% |
| Gmail | 1 | 0.3% |
| Google Cloud | 1 | 0.3% |
| Google Drive | 1 | 0.3% |
| 1 | 0.3% |
Keywords that trigger this capability
Matched as whole words, ignoring case, in a product's name, description and repository topics.
| Keyword | Products matched |
|---|---|
| ocr | 355 |
| optical character recognition | 0 |
| text recognition | 1 |
| tesseract | 2 |
| scan documents | 0 |
| handwriting recognition | 0 |
Segment statistics
Whole catalogue (358 indexed products). Calculated 2026-11-21.
Crowded. Among the largest fifth of capabilities by indexed product count, with launches roughly in step with the catalogue. Size is ranked against all capabilities; momentum compares launches in the last 90 days with the 90 before, relative to the catalogue’s own ratio (62 or more = faster, 38 or less = slower; under 5 dated launches it is not measured). The HHI of 0.132 means stars are spread as if across about 8 equally popular projects — unconcentrated by the common 0.15 / 0.25 thresholds. Stars measure attention, not usage or quality.
Limits
- Classification is by the keywords above. A product that offers this capability without using one of them is not counted; one that uses a keyword in another sense is counted wrongly. Methodology
- Platform reach is protocol-level: it says a platform documents the standard, not that any product here was tested on it. Platforms named by publishers are their own claims.
- Stars belong to repositories. Products in a subfolder of a large repository show that whole repository’s stars and are excluded from the concentration figures.
- Launch counts use each source’s publication date; for auto-discovered repositories that is the repository’s creation date.
Page data last updated .