Data / Repositories / OCR
OCR repositories on GitHub: 17 ranked by stars
17 public repositories tagged OCR are on GitHub, with 54,036 stars between them; 13 had a push in the last 30 days. Most are written in Python (6), Rust (5), TypeScript (2). The most starred: yusufkaraaslan/Skill_Seekers (15,146), run-llama/liteparse (12,824), zyddnys/manga-image-translator (10,492).
SpecStream is the live web data engine for teams and agents. It reads open-source repositories on GitHub and keeps what it reads, and this page groups that reading by topic. Ask for the repositories you track by topic, language, license or activity, and new ones and changes arrive in your sheet, CRM, Slack or agent.
Every repository, most starred first
| Repository | What it is | Language | Stars | Forks | License | Last push | Read |
|---|---|---|---|---|---|---|---|
| yusufkaraaslan/Skill_Seekers | Convert documentation websites, GitHub repositories, and PDFs into Claude AI skills with automatic conflict detection | Python | 15,146 | 1,552 | MIT | Sep 30 | Oct 14 |
| run-llama/liteparse | A fast, helpful, and open-source document parser | Rust | 12,824 | 878 | Apache-2.0 | Oct 9 | Oct 11 |
| zyddnys/manga-image-translator | Translate manga/image 一键翻译各类图片内文字 (no longer working) | Python | 10,492 | 1,069 | GPL-3.0 | Sep 25 | Oct 11 |
| ruvnet/RuVector | RuVector provides High Performance, Real-Time decisions and agent memory , Self-Learning Ai, Vector GNN DB built in Rust. | Rust | 4,565 | 611 | MIT | Oct 14 | Oct 14 |
| zcaceres/markdownify-mcp | A Model Context Protocol server for converting almost anything to Markdown | TypeScript | 2,997 | 255 | MIT | Sep 25 | Oct 14 |
| TimmyOVO/deepseek-ocr.rs | Rust multi‑backend OCR/VLM engine (DeepSeek‑OCR-1/2, PaddleOCR‑VL, DotsOCR) with DSQ quantization and an OpenAI‑compatible server & CLI – run locally without Python. | Rust | 2,183 | 168 | Apache-2.0 | Feb 21 | Oct 11 |
| A9T9/RPA | Browser and desktop automation with an MCP server for AI assistants. Record macros or write JavaScript to automate websites, extract data, and control desktop apps with OCR and… | TypeScript | 2,075 | 419 | Oct 13 | Oct 14 | |
| garylab/MakeMoneyWithAI | A list of open-source AI projects you can use to generate income easily. | Python | 1,112 | 166 | Oct 10 | Oct 11 | |
| SylphxAI/anymd | Any file → clean Markdown for AI agents: PDF, Word, PowerPoint, Excel, EPUB, HTML and web pages, images (OCR), audio and video (metadata, subtitles, transcripts). A fast Rust MCP… | Rust | 1,033 | 90 | MIT | Oct 10 | Oct 11 |
| LingCore/WinShun | Win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… | C++ | 479 | 34 | MIT | Oct 20 | Oct 21 |
| sunriseapps/imagesorcery-mcp | An MCP server providing tools for image processing operations | Python | 333 | 53 | MIT | May 19 | Oct 14 |
| mrpulor-gh/nuphus-mcp | Desktop automation MCP server — computer use for any AI agent: control screen, windows, mouse/keyboard, and Chrome via Model Context Protocol (stdio). Not a DSH plugin — DSH users… | Rust | 325 | 39 | MIT | Oct 13 | Oct 14 |
| shuyu-labs/Windows-MCP.Net | A .NET-based Windows desktop automation MCP (Model Context Protocol) server that provides AI assistants with the ability to interact with the Windows desktop environment. | C# | 233 | 38 | MIT | Nov 27, 2025 | Oct 14 |
| ComPDFKit/compdf-mcp | A lightweight MCP (Model Context Protocol) server for integrating ComPDF AI with Claude Desktop, enabling AI-powered intelligent document processing and data extraction from PDFs… | Python | 97 | 8 | Apache-2.0 | Aug 6 | Oct 14 |
| ben-milanko/dart-pdf | DartPDF is a free, local PDF editor for Android, iPhone, iPad, Mac, Windows, Linux and web. Annotate, fill forms, sign and redact without an account. The repository also contains… | Dart | 88 | 17 | Apache-2.0 | Oct 14 | Oct 14 |
| Mikedev115/Aetox-Harness | Give any AI model a real working environment on your Windows desktop. Aetox is a local-first agent harness that lets AI work across your files, shell, browser, documents, and… | Go | 50 | 15 | Oct 13 | Oct 14 | |
| sassyconsultingllc/SassyMCP | One MCP server, 270 tools, replaces 75+ — files, shell, GitHub, Android, desktop vision, security & forensics, persistent memory. Smart context-saving tool loading, safe-delete… | Python | 4 | 3 | Oct 1 | Oct 14 |
By language
Related topics
- MCP 12
- MCP server 7
- Model Context Protocol 5
- AI agents 5
- PDF 4
- Rust 4
- Windows 4
- AI 3
- LLM 3
- Automation 2
- Anthropic 2
- Markdown 2
Read from GitHub by SpecStream between October 11, 2026 and October 21, 2026; each row shows the day its repository was read. Stars and pushes change every day, and the GitHub page is the current one. Forks and archived repositories are left out.