Allows users to enable Picture-in-Picture mode for HTML5 videos in Safari. It works on websites with hidden video controls. Users can activate PiP by accessing Safari's Webtools Menu and managing extensions.
Text between languages using AI-driven models. Switch between languages in real-time. Copy and paste text for translation. Integrate with browsers as an extension. View content in dual languages side-by-side.
Manage tasks and notes with customizable lists and reminders. Sync data across iPhone, iPad, and iMac. Run Greasemonkey/Tampermonkey in Safari for automation, including pagination, ad blocking, and webpage translation.
Take a photo or select an from the library. Crop and rotate the photo as needed. Convert from the quickly with auto-detected language. Copy or share the extracted through multiple options.
With AI models locally or via cloud APIs. Upload images or text files to improve conversations. Access multiple models including OpenWebUI, Ollama, and Gemini. Send and receive messages with real-time responses.
Close all open browser tabs with a single tap. Save tabs securely within the . Retrieve saved tabs anytime. Organize and manage tabs for improved focus and productivity.
Read articles, videos, and podcasts from multiple sources in one . Sync reading position across devices. Create and share public feeds from any tag. Organize content with unified timelines and custom categories.
Block ads and trackers using predefined rulesets like EasyList and EasyPrivacy. Customize filters by enabling additional rulesets via the options page. Prevent CSS and JS injection-based content filtering without requiring a background process.
Convert posts to shareable images with attribution
Convert Mastodon posts into quote-compatible images with attribution and alternative text. Share generated images to social networks and messaging apps. Create images by pasting post links or using the Share Sheet.
Answer questions using text or voice. Generate images or text based on prompts. Search for information. Provide accurate and relevant answers. Support audio, vision, and text interactions.