This app transforms PDFs, images, and scanned documents into editable text and structured content. It utilizes an on-device AI model for offline processing, preserving your privacy by keeping all data local. Export your recognized content in various formats for easy reuse.
1.3.0
August 9, 2026
Added a new local recognition engine with lower memory requirements, bringing offline document recognition to more devices. Added support for sending recognition results directly to Notion and Obsidian. Added scrolling window capture, region capture, and cropping on Mac.
More感谢反馈的问题，下个版本会修复
No, DocWeave is ad-free, allowing for an uninterrupted user experience.
On-device AI recognition requires an A14 / M1 chip or newer and at least 6 GB of RAM. Specific recognition engines may have higher RAM requirements, with MinerU requiring an iPhone 15 Pro or newer.
The initial download for the local recognition model is approximately 2.5 GB. An internet connection is required for this download, which can be resumed if interrupted.
Yes, DocWeave can recognize paragraph structures, tables, LaTeX formulas, code blocks, and algorithm blocks, going beyond simple plain text.
DocWeave can export recognized content in four formats: reconstructed PDF, Markdown, EPUB, and MinerU packages.
Yes, DocWeave runs its AI model locally on your device. Your documents and recognition results are stored on your device and are not uploaded to any servers unless you choose to export or share them.
The latest version, 1.3.0, was released on August 9, 2026, indicating active development and updates.
DocWeave has a rating of 4.0 stars from 2 ratings, suggesting a generally positive user reception.
