AnyParser
AnyParser, developed by CambioML, is a real-time parser designed to extract content from various file formats, including PDFs, DOCX files, and images. It offers features such as full content parsing, key-value extraction, and table extraction, providing accurate and efficient data retrieval. The platform utilizes advanced Vision Language Models (VLMs) to enhance document retrieval accuracy by up to 2x compared to traditional OCR models, ensuring precise extraction of text, tables, charts, and layout information. AnyParser prioritizes client privacy by processing data locally, ensuring that sensitive information remains confidential and secure. The API is designed for seamless enterprise integration, allowing users to customize extraction rules and output formats according to their specific needs. With support for multiple file formats and a user-friendly interface, AnyParser streamlines data extraction processes, making it a valuable tool for businesses.
Learn more
GLM-4.5V-Flash
GLM-4.5V-Flash is an open source vision-language model, designed to bring strong multimodal capabilities into a lightweight, deployable package. It supports image, video, document, and GUI inputs, enabling tasks such as scene understanding, chart and document parsing, screen reading, and multi-image analysis. Compared to larger models in the series, GLM-4.5V-Flash offers a compact footprint while retaining core VLM capabilities like visual reasoning, video understanding, GUI task handling, and complex document parsing. It can serve in “GUI agent” workflows, meaning it can interpret screenshots or desktop captures, recognize icons or UI elements, and assist with automated desktop or web-based tasks. Although it forgoes some of the largest-model performance gains, GLM-4.5V-Flash remains versatile for real-world multimodal tasks where efficiency, lower resource usage, and broad modality support are prioritized.
Learn more
Screenshot touch
Capture by touch (Notification area, overlay icon, shaking the device). Record video cast of screen to mp4 with options (resolution, frame rate, bit rate, audio). Web page whole scroll capture (with an in-app web browser). There are two ways to scroll capture. One is to share the url in a web browser and select Screenshot Touch. The second is to call the in-app browser directly by pressing the globe icon on the settings page. Drawing on captured image (pen, text, rectangle, circle, stamp, opacity and so on). Sharing screenshot images to other installed apps (user controlled). Capture options (choose the save directory, optional subfolders, file format, jpeg quality, capture delay and so on). Persistent notification (optional): This allows the notification to always remain present which cannot be swiped away. It quickens the accessibility of Screenshot touch. Multiple saving folders: This allows you to create subfolders in a categorising manner for grouping your screenshots.
Learn more
Lightscreen
The easy screenshot tool. Lightscreen is a simple tool to automate the tedious process of saving and cataloging screenshots, it operates as a hidden background process that is invoked with one (or multiple) hotkeys and then saves a screenshot file to disk according to the user's preferences. Choose! Use only the hotkeys, get previews of your screenshots, upload all of them automatically and more. Quickly share what's on your screen by uploading imgur.com and a variety of other image hosts! You can resize and readjust the area of the screen you wish to capture for maximum flexibility. Using an automatic naming system, number your screenshots sequentially or use the date and time. Lightscreen can upload your screenshots directly into imgur.com (using anonymous upload, account upload will come in a later version). The upload menu, available in the Screenshot button and the tray icon gives you access to your Screenshot History and allows you to upload the last screenshot you took.
Learn more
