Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

Maintained fork of Nailuu/wsl-screenshot-cli with Linux clipboard sync and WSL fixes

Paste clipboard images into SSH sessions from Windows Terminal. Ctrl+V inserts a remote file path and uploads via scp — works with Claude Code, Codex CLI, and other terminal AI tools.

Self-hosted GPU-accelerated OCR web app — convert scanned PDFs to searchable PDF, Markdown, or Word. Powered by PaddleOCR. Supports Chinese (Traditional & Simplified) and multilingual documents. Si…

macOS menu-bar utility: three-finger tap → middle click, three-finger swipe → app switcher

The easiest, most secure way to use WireGuard and 2FA.

NVR with realtime local object detection for IP cameras