Search Results for "scroll"

agent-browser is a toolkit that embeds AI agent capabilities directly into the web browser, enabling agents to interact with web content, scripts, and user actions while maintaining security boundaries that respect user privacy and browser constraints. It effectively provides a sandbox where AI agents can read, scroll, click, and interpret pages in context, allowing them to automate workflows, answer questions about page content, or generate structured summaries directly from the user’s current tab. The project emphasizes standards and safety, defining interfaces that let agents access DOM data, interpret events, and generate actionable insights without exposing sensitive credential-level access or violating policy boundaries. ...

...The goal is to build an editor that uses Neovim inside with many of the convenience GUI features similar to those present in modern editors. We mainly use Swift, but also use C/Objective-C when where appropriate. Markdown preview, generic HTML preview (retains the scroll position when reloading), fuzzy file finder a la Xcode's "Open Quickly". Trackpad support, pinching for zooming and two-finger scrolling. Ligatures, turned off by default. Turn it on in the Preferences. Command line tool, (Simple) file browser. Flexible workspace model a la JetBrain's IDEs.

...Under the hood it uses a modern browser (installed via a one-time shot-scraper install step) and exposes options for viewport size, full-page versus clipped screenshots, and device emulation. Beyond simple captures, it can run custom JavaScript before taking the shot, allowing you to open menus, scroll, or manipulate the DOM so the screenshot reflects the desired state. The project is deeply integrated with automation workflows: examples show it running in scheduled jobs, GitHub Actions, and bots that publish screenshots to social media or use them in docs. It ships with detailed documentation, a tutorial, and a template repository that lets you spin up an automated screenshot pipeline.