
Open-source skill that learns any brand and generates a complete design system for Claude Code and Codex.
By Tanmay Verma, Founder · Last verified 03 Jul 2026
In short
Hue — Open-source skill that learns any brand and generates a complete design system for Claude Code and Codex. Best for Designers wanting consistent AI-generated UI, Developers using Claude Code or Codex for frontend work, Solo founders building prototypes with brand consistency. Free to use.
See what real users actually say. We scan live discussions, reviews and complaints across the web and hand you an honest verdict — in under a minute.
3 free scans · no card needed · downloadable report
Hue delivers exactly what it promises: a dead-simple way to make AI assistants generate on-brand UI. It's a brilliant, lightweight solution for anyone tired of generic components—and free makes it a no-brainer try.
Compare with: Hue vs Subframe, Hue vs Draftbit, Hue vs Motiff
Last verified: July 2026
How likely is Hue to still be operational in 12 months? Based on 4 signals — momentum (how recently it shipped), wrapper dependency, revenue model, and web presence.
Last calculated: July 2026
How we score →Hue is a free, open-source skill for AI coding assistants like Claude Code and Codex. Instead of producing generic, one-size-fits-all UI components, Hue learns your brand from a URL or screenshot and generates a complete design system with tokens, typography, radii, elevation, buttons, inputs, cards, and 30+ components—including dark and light mode. Install it once into your AI's skills folder, and every UI your assistant builds will match your brand perfectly. Hue is built for designers, developers, and teams who want consistent, on-brand AI-generated interfaces without manual tweaking. It works offline against your own model, requires no account, API key, or subscription. Simply clone the repository into Claude's skills folder or Codex's agents folder, and it's ready to use. What sets Hue apart is its focus on capturing an entire design system—not just a color palette or a vibe. It outputs a full, browseable component library with all generated files, making it easy to inspect and refine. The project is MIT-licensed and maintained by a solo developer in Berlin, Dominik Martin.
If you use Claude Code or Codex and want UI components that actually match your brand, Hue is the best free solution we've seen. It captures a full design system from a single URL or screenshot—colors, typography, spacing, dark mode—and installs as a single skill folder. No accounts, no API keys, no subscriptions. We'd reach for this when we need fast, on-brand prototypes or want to standardize AI-generated UI across a team. It's especially good for solo founders who can't afford a dedicated designer but still want consistent interfaces. Where it bites: Hue requires Claude Code or Codex. If you use Cursor, Windsurf, or other AI coding tools, you'll need to wait for support—or adapt it yourself. Also, it generates HTML component libraries, not editable Figma files, so designers may still want handoff capability. Compared to alternatives like Supabase UI or Tailwind UI, Hue is less about pre-built themes and more about dynamic brand capture. It's not a replacement for those if you want a ready-made library, but it's better if you need to match an existing brand. In practice, one-shot generation works well for most brands, but highly complex or busy sites may need a second pass. The maintainer is responsive, and being MIT-licensed means you can modify it freely. Verdict: If you use Claude Code or Codex, install Hue. It's free and improves output quality immediately.
Free, no signup — tell us your goal and get tools matched to your budget & existing stack.
Project the real annual outlay, including the implied monthly cost when only an annual tier is published.
Vendor list price only. Add-on usage, seat overages, and contract minimums are surfaced under Hidden costs & gotchas.
Common stack mates teams adopt alongside Hue, with the specific reason each pairing earns its keep.
Used Hue? Help shape our editorial sentiment research.