Directory
Published directory entries matching your search.
A Mac and Windows application that extracts burned-in and hardcoded subtitles from video into editable, time-synced SRT files. It supports Chinese, English, Japanese, Korean and other languages, with automatic timeline alignment, batch processing and local processing so files stay on the computer.
gImageReader is a Gtk/Qt front-end to tesseract-ocr. It imports PDF documents and images from disk, scanning devices, clipboard and screenshots, can process multiple images and documents at once, and recognizes text as plain text or hOCR documents. Recognized text is shown next to the image and can be post-processed with spellchecking.
GitLab snippets lets users store and share bits of code and text with other users. Snippets can contain multiple files and support version control, commenting, cloning, embedding, downloading, and syntax highlighting. Users can create personal snippets independent of any project or project snippets tied to a specific project, and manage them through the GitLab user interface, the GitLab for VS Code extension, or the glab CLI.
An image processing tool that can convert wallpaper color schemes and palettes, perform OCR with traditional and hybrid VLMs, compress images, extract color palettes, upscale images with adversarial networks, and offer additional image processing functionality.
HedgeDoc, formerly known as CodiMD, is an open-source, web-based, self-hosted collaborative markdown editor. Users share a note link to collaborate in real-time on notes, graphs and presentations. It is licensed under AGPL 3.0, and its source code is available on GitHub.
i2ocr is a free online OCR tool that extracts text from images and PDFs using AI-powered optical character recognition. It supports 128 languages and converts files into editable, searchable text. The service is accessible via its website.
ihatepdf is a free online PDF service accessible via the ihatepdf.cv domain, offering over 60 PDF tools with no watermarks, required file uploads, or sign-up steps. All processing occurs in the user's browser, files remain on their device, and the tool works offline. Supported functions include merging, splitting, compressing, editing, performing OCR, and encrypting PDFs, and the service is free to use permanently.
ImgOps is a meta-tool for online image operations. A user enters an image by pasting, dragging and dropping, or a URL, then chooses an online image utility. The page lists supported operations including reverse image search, EXIF viewing and removal, editing, format conversion, OCR, and animated GIF utilities. Uploads are stored temporarily in a one-hour cache.
KanjiTomo is an OCR program for identifying Japanese text from images, optimized for kanji recognition. Pointing the mouse at any image on screen performs kanji and dictionary lookup at the same time, and both horizontal and vertical text are supported. Java is required, and it has been tested on Windows 10.
Labelbuddy is a desktop application for text labelling, tagging spans of text with different labels. According to its documentation page, it is an open-source, lightweight application supporting sequence labelling with predefined labels or free-form annotations. It can be installed on Linux, Windows or MacOS, and data can be imported and exported using JSON, JSONLines or plain text formats.
Labelbuddy is an open-source desktop GUI application for annotating documents, developed on GitHub. According to its documentation, it can be used for tasks such as Named Entity Recognition, sentiment analysis and document classification. The documentation states that it works completely offline and that its database is an ordinary file. Import and export use JSON, JSON Lines or plain text formats.
LlamaIndex is a platform focused on AI agents for document optical character recognition (OCR) and workflow automation. Its LlamaParse tool is designed to process complex documents including those with tables, charts and images, and can perform parsing, extraction, splitting, classification and indexing of document content.
NormCap is an OCR-powered screenshot tool that captures text instead of images. It uses Tesseract language models for text detection and supports QR and barcode scanning. Detection is performed on the device and no telemetry data is collected. It is available for Windows, macOS and Linux and is licensed under GPLv3.
Creates or edits images with generative models and visual controls.
Creates or edits images with generative models and visual controls.
OCRmyPDF is a software tool that adds an OCR text layer to scanned PDF files, making the content of scanned documents searchable. It is maintained as an open source project on GitHub.
OpenPaper is the official site for Paperwork, a personal document management tool. It allows users to scan or import personal documents, search for them using keywords, store files in a single synchronizable directory, and add labels for organization.
OSINT.SH is a collection of information gathering tools. It lists tools for finding public cloud buckets, subdomains, DNS history, reverse IP lookups, technology detection, certificate searches, DNS lookups, reverse Google Analytics and AdSense IDs, WHOIS history, reverse WHOIS, reverse domain searches, OCR text extraction, MD5 hash guessing, SSL checking, IP geolocation, and reverse MX and name server records.
Paper2GUI is an AI desktop application toolbox that is free and ready to use out of the box. It supports more than 10 AI models covering speech synthesis, video frame filling, video overscoring, target detection, image stylization and OCR recognition, on Windows, Mac OS and Linux.
Command-line document and bibliography manager for papers, PDFs, notes, and references.
Papra is an open-source document archiving platform for organizing, securing and archiving documents. It offers organizations, document tagging, search, a developer API, webhooks, CLI and SDK, plus email ingestion that imports attachments. The project is available on GitHub under the AGPL-3.0 license and can be self-hosted. Paid plans add storage, members and intake email addresses.
Document management app for saving, organizing, searching, and tracking personal files.
Pleco is a Chinese language reference and learning app for iPhone, iPad, and Android. It offers OCR lookup, handwriting lookup, licensed dictionary databases, audio recordings, flashcards, a document reader, a screen reader for Android, and animated stroke order diagrams.
Scanner is a Windows application for WIA-compatible scanners that saves multiple pages as a single PDF or separate images. It includes a built-in editor for cropping, rotating, drawing with Windows Ink, renaming files and deleting or reordering pages, and is available in the Microsoft Store.
