ai-ocr 开源项目推荐（31 个）

ruvnet /RuVector

RuVector 提供高性能、实时决策与智能体记忆、自学习 AI，以及使用 Rust 构建的 Vector GNN DB。

samestrin /llm-pdf-ocr-api

A Python-based REST API for PDF OCR using AI models with PyTorch and Transformers that runs in a Docker container.

37jahangir /ocr-snipping-tool

A snipping tool to Extract Text By snipping using cursor from anywhere on the screen.

ceodaniyal /free-llm-image-to-text

Free OCR powered by LLMs using OpenRouter — extract text from images with no API costs. Works with image URLs and Base64 inputs using free vision-capable models.

kourdroid /OCRAgent

Ironclad-OCR is an asynchronous invoice ingestion and extraction service built for vendor PDFs that do not share a single stable layout.

Captcha-Sonic /CaptchaSonic-BLS

AI CAPTCHA solver for BLS visa appointments. Auto-solves number-grid CAPTCHAs on all BLS portals. ⚡

ceodaniyal /local-llm-ocr-ollama

Free, offline OCR using local LLMs with Ollama. Convert images to text with vision-enabled models running entirely on your machine — no cloud, no API costs, full privacy.

sTharun5 /Automation

An autonomous, AI-powered On-Duty (OD) approval ecosystem for BIT. Featuring DocSense OCR, intelligent fraud detection, and automated multi-role workflows. 🎓🤖🛡️

subhashladumor1 /laravel-ai-docs

🤖 Laravel AI Docs — Intelligent PDF & OCR Processing for Laravel. Convert PDF to JSON, Extract Tables, Ask PDF with AI, Image & Audio to Text (GPT, Claude, Gemini)

AndreaBonn /BetTracker-by-Bonn

Stop losing track of your bets. BetTracker lets you log sports wagers, scan bet slips with AI-powered OCR, and automatically fetches match results so you always know where you stand. Push notifications when bets settle, detailed stats, and shareable slips. All in one sleek mobile-first app.

ocean-master0 /unlimited-ocr-colab

Free, open-source Google Colab notebook that converts PDF & image files (JPG, PNG, BMP, TIFF, WEBP) into clean Markdown using Baidu's Unlimited-OCR (MIT license, 93%+ OmniDocBench). No API key, no cost — runs on free Colab GPU. PDF to Markdown, OCR, document parsing, image to text converter.

code-vygr /local-llm-ocr-ollama

🖼️ Extract text from images locally using Ollama's LLMs—100% free, offline, and private. No API keys or cloud costs necessary.

wolfg1969 /retroarch-ai-translate

基于 Vision LLM 的实时游戏截图翻译服务，通过 RetroArch AI Service 协议在画面叠加层显示翻译结果。

JyotirmoyBhowmik /InvoiceFlow

"InvoiceFlow" : Exchange-Online Invoice Ingestion, AI-OCR & SAP ECC Export Platform

rahulpmishra /courier-parcel-extractor

AI-powered courier parcel extraction dashboard using Gemini, FastAPI, PHP, and Google Cloud to convert parcel images into validated CSV/JSON records.

simply-mihir /ResQ

ResQ is an enterprise-grade emergency intelligence platform that accelerates life-saving admissions. Engineered on a distributed microservices architecture, it seamlessly bridges patients and hospitals through real-time geospatial routing, event-driven fleet tracking, and secure AI-extracted medical vaults.

JiyaroJoseph /Vyapaar-Connect

QR-based loyalty management app for small vendors with Google Sign-In and AI-assisted menu extraction.

csfahad /writeshift

Transform handwritten notes into clean, editable digital text in seconds. Multilingual support (English & Hindi), real-time image preprocessing, inline editing, and one-click export to TXT, JPG & PDF. Built with React, Express & Bun.

katsushi2441 /kocrwork

Kurage OCR Work — OCRエンジン（PaddleOCR・Tesseract・Docling・生成AI）を切り替えて注文書を読み比べ、受注登録まで。画面・API・MCP

SintaxBaz /Vyapaar-Connect

QR-based loyalty management app for small vendors with Google Sign-In and AI-assisted menu extraction.