Text Grab is a Windows OCR tool that turns screenshots into editable text.

It can run as a background process with optional notifications.

@githubforks

DocStrange extracts data from documents, images, PDFs, Word, PowerPoint, or URLs into Markdown, JSON, CSV, and HTML.

It uses structured data extraction and advanced OCR.

@githubforks

Curses converts speech to text and subtitles in kilobytes for OBS, VRChat, Twitch chat, and Discord.

@githubforks

Plexe allows you to create machine learning models by describing them in plain language. Just explain what you need, provide a dataset, and the AI-based system builds a fully functional model.

@githubforks

Web-ScreenRec records the screen with no installation required.

@githubforks

Render deploys sites, APIs and full workflows free. No payment, no card.

The free tier includes up to 5 GB bandwidth and 25 services, plus custom domains and AI agents.

For pet projects and MVPs, that removes the usual infrastructure cost at the experimentation stage.

@githubforks

Docspell sorts piles of scanned documents with minimal effort.

It handles files from scanners, email, and other sources.

@githubforks