Open-source projects tagged “ocr”

A 9B-parameter open-weight multimodal model for visual understanding, spatial reasoning, agentic tool use, and embodied-AI research, built on Qwen3.5 and C-RADIOv4-H.

Local-first macOS app that lets you search photos and video frames in any folder by describing them in plain language, with on-device AI.

Offline, privacy-first PDF toolkit for Android that merges, splits, compresses, converts, signs and annotates PDFs entirely on-device.

A unified multimodal model that handles computer vision tasks like detection, OCR, segmentation, depth and multi-view geometry through text and image generation.

Open-source Android and iOS app for scanning documents into PDFs with OCR, built with NativeScript, OpenCV and Tesseract.

A privacy-first PDF toolkit that runs entirely in the browser, offering 50+ tools to edit, merge, convert and secure PDFs, and self-hostable.

A Docker-based microservice and Gradio UI that segments PDF pages into titles, text, tables, pictures and more, with OCR and Markdown/HTML conversion.