Older catalogue

Keep research and ideas connected in a visual knowledge workspace instead of a pile of isolated notes.

Get a quick summary and transcript from a YouTube video without leaving the watch page.

Add and detect localized watermarks in AI-generated speech with an open-source Python toolkit.

Select text inside an image, video, or PDF and copy or translate it.

Turn a recording into text for captions, notes, and content repurposing in a few minutes.

Get gift ideas matched to a recipient, their interests, and your budget.

Let an AI agent build a video from code, then render the result deterministically.

Get the transcript and useful takeaways from a video or link without creating an account.

Turn a video, social link, or audio file into a transcript, subtitles, and a summary.

Loop, slow down, and repeat a precise part of any YouTube video.

Fix, remove, or improve a photo in the browser with a short prompt or a simple tool.

Generate, extend, and edit music or sound with open Stable Audio model resources.

Turn one reference image into a textured, PBR-ready 3D asset for games, AR, and prototyping.

Turn a moving camera stream into a continuously updated 3D scene for mapping and robotics.

Use one assistant for chat, web research, document summaries, math help, and limited media generation.

Connect an AI agent to a real browser through an editable Chrome harness.

Sketch, furnish, and share a building concept in a browser-based 3D workspace.

Run a personal task-doing agent locally or in the cloud with a guided setup.