HN Showcase
Back to browse
AI IDE that converts websites and designs into code

AI IDE that converts websites and designs into code

by aliadelelroby·May 28, 2026·2 points·1 comment
Visit ProjectView on HN

AI Analysis

●●SolidSlickSolve My Problem

Design canvas inside VS Code beats Figma plugin export workflows.

Strengths
  • •AI reads design canvas layers directly instead of vague text descriptions.
  • •Figma-compatible clipboard means no plugins or export steps needed.
  • •Inline diffs let you review AI changes before applying them.
Weaknesses
  • •Alpha stage with request-access gate makes real evaluation impossible.
  • •Figma-to-code space already has Anima, Builder.io, and v0.dev competitors.
Target Audience

Frontend developers and designer-developers who work with Figma

Similar To

Cursor · v0.dev · Builder.io

Post Description

Hi HN Community! I'm Ali, Founder of Velork. I built Velork because I wanted something that I can really depend on to build production and client UI work, something that's professional enough that I can use day in and day out in my freelancing business.

Velork is a full IDE built on VS Code. It combines design directly into the editor through a new tab called Canvas, so you never have to leave your coding environment.

It lets you copy Figma designs directly into it and build clean code based on them. You can also take inspiration from existing sites and build a new UI that remixes and combines them into something new.

AI has full access to your design canvas and can read every layer, element, and structure inside it. So instead of describing your UI to the AI, you just point at it and it understands the full context.

I need about 10 to 15 people to try out the alpha version. I already have 3 to 4 people testing so there are about 11 spots remaining. This will be an early stage version and you'll be contributing to the product directly based on your feedback.

If you're interested, add your email at velork.com and I'll reach out with access :)

Similar Projects

Design●●Solid

Design Memory – Extract design systems from live websites via CLI

Playwright-driven crawling + deterministic token extraction plus an LLM for semantic labeling is a clever pipeline — it doesn’t just scrape CSS, it produces an AI-optimized .design-memory folder with tokens, component recipes, and multi-page merge/diff capabilities. Expect variable fidelity on highly dynamic or framework-heavy sites since the approach depends on selector heuristics and an API key, but the CLI commands (learn, install, diff) and docs show this is more than a research sketch.

WizardryNiche Gem
saleban1031
104mo ago