Nicheloom visits: 60,733 all-time · 7,913 in the last 7 days

The opportunity tracker for new startups.

Today: 1,919 launches · Niche of the day: browser-based utility tools · See what launched today →

Understudy

Teach a desktop agent by demonstrating a task once

Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.

Want to reach these readers? Sponsor an issue.

I built Understudy because a lot of real work still spans native desktop apps, browser tabs, terminals, and chat tools. Most current agents live in only one of those surfaces.Understudy is a local-first desktop agent runtime that can operate GUI apps, browsers, shell tools, files, and messaging in one session. The part I'm most interested in feedback on is teach-by-demonstration: you do a task once, the agent records screen video + semantic events, extracts the intent rather than coordinates, and turns it into a reusable skill.Demo video: https://www.youtube.com/watch?v=3d5cRGnlb_0In the demo I teach it: Google Image search -> download a photo -> remove background in Pixelmator Pro -> export -> send via Telegram. Then I ask it to do the same for Elon Musk. The replay isn't a brittle macro: the published skill stores intent steps, route options, and GUI hints only as a fallback. In this example it can also prefer faster routes when they are available instead of repeating every GUI step.Current state: macOS only. Layers 1-2 are working today; Layers 3-4 are partial and still early. npm install -g @understudy-ai/understudy understudy wizard GitHub: https://github.com/understudy-ai/understudyHappy to answer questions about the architecture, teach-by-demonstration, or the limits of the current implementation.

HN · launched Mar 12, 2026 · 120 upvotes (top 7%) · 0 views

Niche: computer and browser automation agents · 127 launches, 0 in the last 7 days ▼ -100% · Explore this niche →

Category and tags

  • Horizontal
  • Agent / copilot
  • Prosumer
  • AI-native
  • Commercial product

Visit website ↗ Source listing ↗

Could you build this?

Partial Recording user screen events and synthesizing them into cross-platform OS automation (combining OS accessibility APIs, computer vision, and shell execution) involves complex low-level OS plumbing.

What it would actually take: The agent runtime requires native OS hooks (macOS Accessibility APIs / Windows UI Automation / Linux AT-SPI) combined with global input event listeners and screen capture (CoreGraphics/DXGI). It needs a multimodal AI pipeline (vision-language model) that translates user demonstrations into structured execution plans, resolving UI coordinates and fallback strategies when visual elements change. Expertise in OS-level automation, accessibility trees, and robust headless execution is required.

Discussion

20 comments analyzed.

Competitors mentioned: Claude Chrome extension

Concerns raised: macOS only, not available for Windows or Linux, Claude Chrome extension has website blocks on financial sites, Agentic systems introduce inherent uncertainty, Demo was cherry-picked

Feature requests: Cross-platform support (Windows, Linux), Agent proactive error recovery with human feedback

Competitors

Other products that read as similar to this one : 45 launches clear the similarity bar, closest 8 shown.

Attention rank: #8 of 46 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).

Launched 121 days after the earliest competitor.

The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.