Directory
Published directory entries matching your search.
Windrecorder is an open-source memory search app for Windows that records screen activity locally and allows rewinding seen content. It supports queries through OCR text or image description and provides activity statistics. It also offers OCR engine options and a web interface.
2OCR is a free online OCR tool that converts images and PDF files into searchable PDF, PDF/A or text output. It accepts formats including jpg, png, tiff, bmp, heic, webp, pdf, doc and xls, requires no registration or email address, and supports multiple languages.
Capture2Text is a free, GPL-licensed Windows utility that OCRs a portion of the screen using a keyboard shortcut and saves the resulting text to the clipboard by default. It supports Windows 7, 8/8.1 and 10 and packages several OCR languages, with additional language dictionaries installable.
Proton Docs is a secure online document collaboration tool offered by Proton. It supports real-time co-authoring, safe document sharing, cross-device access, and end-to-end encryption. The tool also includes features for tracking changes and suggestions, gathering feedback and comments, and user-controlled sharing.
AnyTXT Searcher is a desktop full-text search application that extracts text from documents and indexes it for searching. It supports formats including plain text, Word, Excel, PDF, and images via offline OCR, and runs on Windows, MacOS, and Linux.
Arch Tools provides one API key for 63 tools aimed at AI agents and developers, covering web search, scraping, AI generation, OCR, transcription, crypto data, email and utilities. It supports REST and MCP protocols and offers two authentication methods: an API key or per-call x402 crypto payments in USDC on Base.
BentoPDF is a free, open-source online PDF toolkit that processes files locally in the browser using WebAssembly, so files are not uploaded. It offers over 100 tools for merging, splitting, compressing, converting, editing, annotating, signing and filling PDFs, and is described as self-hostable with offline OCR.
CatchTheTornado/text-extract-api is a GitHub repository for an open-source document extraction and parsing API. It supports PDF, Word, PPTX, and other document and image formats, uses modern OCR technology and Ollama-supported AI models, can anonymize documents and remove personally identifiable information (PII), and converts content to structured JSON or Markdown output.
CircleToSearch is an Android app that performs reverse image search by circling content on the screen, with support for multiple search engines including Google Lens, Bing, Yandex, TinEye, ChatGPT and Perplexity. It offers offline OCR text recognition, offline QR detection and works on devices running Android 10 or later without Google Play Services.
Copyfish is an open-source OCR software and text extractor that copies, pastes and translates text from images, videos or PDFs. It runs in Chrome, Edge and Firefox and works on Windows, Mac and Linux. A desktop capture feature requires the XModule2 helper app.
ICIJ document analysis platform for searching, indexing, and investigating large document collections.
dDocs is a privacy-first, end-to-end encrypted document editor for real-time collaboration. It is positioned as a self-sovereign alternative to Google Docs that does not conduct user surveillance or train AI on user content.
Collection of free web-based tools for editing, converting, merging, splitting, compressing and otherwise manipulating PDF files. Processing happens in the browser with no installation required. Categories cover organizing PDFs, converting to and from PDF, signing and security, and viewing and editing, including OCR cleanup of scans.
Paperless-AI is an automated document analyzer for Paperless-ngx that analyzes and tags documents using OpenAI API, Ollama, Deepseek-r1, Azure and other OpenAI API compatible services. The repository states it is currently not maintained, and notes uncertainty about continuing maintenance.
Doc Brown's School Science Revision Notes and Quizzes is a science revision website that began in 2000 as a chemistry site and has since expanded. It offers revision notes and quizzes for biology, chemistry and physics at lower secondary, GCSE, IGCSE and advanced level, keyed to UK exam boards including AQA, Edexcel, OCR, WJEC and CCEA.
Docmost is an open-source, self-hosted collaborative wiki and documentation tool presented as an alternative to Notion and Confluence. It offers real-time collaborative editing, team spaces with permissions, comments, page history, public sharing, nested navigation and diagramming tools. An optional enterprise edition adds SSO, AI and API access. It can run in air-gapped environments with no external dependencies.
Docmost is an open source collaborative wiki and documentation software platform. It is designed as an open source alternative to existing tools such as Confluence and Notion. The project is hosted on GitHub and available for use and community contribution.
Docspell is an open source document management system designed to help users organize documents sourced from scanners, emails and other inputs with minimal effort. The project provides public documentation, a demo instance for testing, and accepts community contributions and support.
Open source document signing platform for forms, PDFs, templates, and e-signature workflows.
DocuSeal is an open source platform for digital document signing and processing. It provides a PDF form fields builder and lets PDF forms be filled and signed online on any device through a mobile-optimized web tool.
A free, open-source DOCX editor that runs entirely in the browser. It opens, edits and saves .docx files with formatting, tracked changes, comments, tables and images, without sign-up or server upload. React and Vue versions are also mentioned.
Docx Editor is an open-source WYSIWYG .docx editor library for React and Vue, supporting canonical OOXML, tracked changes and real-time collaboration. It includes a headless layout engine that runs on client and server, plus a PDF generation engine for editing, rendering and export.
Eden AI offers a unified API for accessing large language models and specialist AI models, including OCR, speech, translation and vision. It standardizes requests, responses, authentication, billing and monitoring across providers, and supports routing requests by cost, performance and region.
Falcon LLM is described as a generative large language model that supports applications and use cases. The site presents models in the Falcon LLM family, including Falcon-H1 and Falcon-E, and lists Falcon-H1 model insights. It also references Falcon Arabic for Modern Standard Arabic and dialects, and names Falcon-Emirati, Falcon-ASR and Falcon-OCR-Arabic.
