Directory
Published directory entries matching your search.
Backprop is a Python library, installable via PyPi, that enables use, finetuning and deployment of machine learning models. It provides task interfaces for conversational question answering, text classification in over 100 languages, image classification, summarisation, emotion detection and text generation, and models can be finetuned with a single line of code.
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.
MemFree is a hybrid AI search engine and AI page generator. It provides accurate answers sourced from the internet and a user's personal knowledge base. It supports multiple AI models, search engines, and input formats including text, images, and local files. It can generate production-ready user interface pages from text or image inputs in seconds.
ImageBind is a PyTorch implementation with pretrained models from FAIR, Meta AI. It learns a joint embedding across six modalities: images, text, audio, depth, thermal, and IMU data. The release includes code and model weights under the CC-BY-NC 4.0 license.
Text2img is a console application that converts text files to images. It accepts an optional codepage argument, with /L listing available codepages, and an optional output file; if none is given, the input file's extension is swapped for ".png". The README notes the maximum image dimensions are 32767*32767 pixels and that a 32bpp in-memory image would need about 4 GB of RAM.
Barcodrod.io is a free barcode and QR code toolkit for Windows 10/11. It decodes 17 barcode types from images, clipboard, webcam or the Snipping Tool, and creates 13 barcode types from text. It is built on WinAppSDK, WinUI3, .NET 9 and the ZXing.Net library.
Amuse is an open-source local AI tool hosted on GitHub. It supports generation of images, videos, audio, and text, with dedicated pipelines for each media type, and welcomes community contributions to its development.
Automated machine learning for image, text, tabular, time-series, and multi-modal data.
Clip-as-a-service is an open-source tool that provides scalable embedding, reasoning, and ranking capabilities for images and text using the CLIP model. It is maintained as a public repository on GitHub under the jina-ai organization, with documentation and installation guides available.
Copycat is a browser extension for copying content from web pages. It supports Chrome, Edge and an old Firefox version, and can copy tab titles, links and selections as plain text, HTML, Markdown and other formats. Images, audio and video can also be copied in some formats.
Copyfish is a free Chrome extension that enables users to copy, paste, and translate text extracted from images, videos, and PDFs. It is intended for language learners, manga readers, and developers, and its source code is hosted on GitHub.
DeepDetect is a deep learning runtime, command-line tool and REST server for training and inference. It provides Python wheel variants for CPU and GPU environments and a command-line interface with profiles such as object detection and semantic segmentation. YAML configuration files make runs repeatable. It handles images, text, tabular data, time series, object-detection boxes and segmentation masks through a single API surface.
Discover is a Discord overlay for Linux written in Python using GTK3. It can show who is currently talking on Discord or display text and images from a preconfigured channel. It is fully customisable and can be positioned anywhere on the screen. The project states support for X11 and wlroots-based environments and offers command-line controls for starting, hiding and voice actions.
GSlides Maker is a command-line tool that generates Google Slides presentations from Wikipedia content. The generated presentation uses a blank theme, and users can then choose a Google Presentation theme, which changes the font style, size and color. The beta version produces only text content and does not yet produce slides containing images.
Handwriting-OCR is a project that tries to create software for recognizing handwritten text from photos, including Czech language, using computer vision and machine learning. Recognition is divided into four steps, from page detection through word separation and normalization to character recognition. It is written in Python 3.6 with Jupyter Notebook, and the repository was archived by its owner.
A curated GitHub list of artificial intelligence tools. It groups entries into categories such as AI text, coding, generative images, video, audio, marketing, phone call agents and learning resources, and links to models including GPT-3, GPT-4, LLaMA and Claude 3.
microMathematics Plus is an open-source Android scientific graphing calculator and function plotter oriented around worksheets. It enables users to perform mathematical calculations in naturally readable form, create interactive formula collections, edit mathematical identities live with high accuracy, and store documents containing formulas, plots, text and images. The app includes no ads, trackers or telemetry, supports common mathematical operations and SI and non-SI units, and works on smartphones and tablets in portrait and landscape modes.
Museum of All Things is a free, open-source project that builds a nearly infinite 3D museum procedurally generated from Wikipedia content. Each exhibit shows the corresponding Wikipedia article text as wall plaques and pulls relevant images from Wikimedia Commons. Hallways connect each exhibit to others linked from the current exhibit's Wikipedia page, allowing endless exploration. The project is hosted publicly on GitHub.
NotCurses is a library for building complex text user interfaces and character graphics on modern terminal emulators. It supports vivid colors, multimedia, threads and Unicode, and includes visual features such as images, fonts, video, sprites and transparent regions. It is described as not a source-compatible X/Open Curses implementation nor a replacement for NCURSES.
An open-source tool that captures digital history through regularly taken screenshots. Text and images in the screenshots are analyzed and made searchable, and users can scroll back through past activities. It is described as cross-platform.
PyOD is an open-source Python library hosted on GitHub for anomaly detection across tabular, time series, graph, text, image and audio data. It includes over 60 anomaly detectors, an ADEngine orchestration tool, and supports agentic workflows for use with AI agents.
Qwen3-Omni is a natively end-to-end omni-modal large language model developed by the Qwen team at Alibaba Cloud. It can process text, audio, images, and video inputs, and generate speech in real time. The project's resources are hosted on a public GitHub repository.
ShareX-Upload-Server, also called ShareS, is a feature-full, stable Node.js file server compatible with ShareX. It supports uploading images, videos, code, and text, provides markdown rendering, password-protected uploads, Discord-based logging and administration, URL shortening, and a full front end, and can be used standalone or via reverse proxy.
SVGo is a Go language library for SVG generation. It supports common SVG elements including shapes, lines, text, paths, images, and gradients, and is hosted as an open-source project on GitHub.
