xushengfeng /eSearch-OCR

BobLd/RapidOcrNet

Cross-platform OCR processing using PaddleOCR ONNX models (v4 / v5 / v6). Based on RapidAI's RapidOCR

Azyrn/Scanly

Scanly — a fast, private document scanner for Android. On-device OCR, barcode & product lookup, and AI text extraction with translation. Free, open-source, and built with Material 3.

opendatalab/MinerU🔥 active

▲ +401 ★ this week

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

hiroi-sora/Umi-OCR

▲ +157 ★ this week

OCR software, free and offline. 开源、免费的离线OCR软件。支持截屏/批量导入图片，PDF文档识别，排除水印/页眉页脚，扫描/生成二维码。内置多国语言库。

bytedance/Dolphin

The official repo for “Dolphin: Document Image Parsing via Heterogeneous Anchor Prompting”, ACL, 2025.

RapidAI/RapidOCR🔥 active

▲ +63 ★ this week

📄 Awesome OCR multiple programing languages toolkits based on ONNX Runtime, OpenVINO, MNN, PaddlePaddle, TensorRT and PyTorch.