Layoza

io.github.layozaPublished by GitHub account layozav0.1.4Updated Nov 2, 2026

Design systems, layout and motion guidance for AI agents, plus headless Chromium visual QA.

Overview

AI-generated overview

Layoza gives an assistant design-system, layout and motion guidance for building UIs, plus headless Chromium visual QA of the result.

What you can do
  • Read a codebase or live site into design tokens, site DNA and a component inventory
  • Generate an industry read, design dials and three distinct creative directions for a brief
  • Deal niche-aware motion mechanics and animation recipes
  • Run headless Chromium QA at three widths: screenshots, accessibility, performance and functional checks
  • Create baselines, compare before and after, roll back and export reports
  • Search bundled UX guidelines, chart picks, stack notes and icon guidance
When to use it
Useful when an assistant writes or restyles front-end pages and you want output that follows a coherent design direction and is checked in a real browser. It fits new sites, extending an existing site, accessibility and usability fixes, and redesigns with a rollback path.
Requirements
Runs locally via npx as a stdio process; Node.js 18 or newer. Prebuilt binaries cover Windows x64, macOS and Linux x64/arm64; other platforms compile from source and need Rust. Visual QA needs Playwright with Chromium installed. Optional environment variables configure QA timeout, Playwright location and engine.
Before you install
It writes files into your project (design documents, a per-project ledger, baselines) and can roll back changes, so review what it modifies. Visual QA launches a browser and fetches pages you point it at; treat inspected page content as untrusted. Performance checks are opt-in.

Installation

In SourceWeft

  1. Open Layoza in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

[Layoza]

Layoza — design engineering for AI agents

An open-source MCP server + agent skills that turn Claude Code, Cursor, Codex, OpenCode, Antigravity and Windsurf into a UI/UX design expert: it reads your site's design DNA, picks motion that fits the brief, and checks every change in a real Chromium browser.

[npm] [License: MIT] [MCP] [WCAG 2.2 AA]

[Four websites built by an AI agent using Layoza from one-line briefs: a kinetic agency site, a linen store, a multi-shop sales dashboard and a seafood restaurant, each shown at desktop and phone width]

[Animated preview of the showcase video: Layoza next to Claude frontend-design, impeccable, ui-ux-pro-max, taste-skill and plain Claude on the same brief, recorded live in a real browser]

▶ Download the full 2½-minute showcase (MP4, 17 MB): all four briefs, recorded live in Chromium

bash
npx layoza init            # adds the skills + MCP server to every agent it finds in this projectnpx layoza qa index.html   # design and usability: contrast, overflow, focus, menu, screenshots

Then just talk to your agent. Example prompts:

text
Build a homepage for a family-run bakery in Leeds. Warm, not twee.Add a pricing page that matches the rest of this site.Our dashboard feels cluttered. Fix the design without changing the brand.Redesign the agency homepage with a kinetic hero, but keep every page and form working.Check this page on mobile and fix anything a visitor would trip over.

Why

Layoza exists so AI-built sites stop looking like slop. Every design it helps make should be unique: never a copy, a re-skin or a repeat, from the nav through the hero and every section to the footer, built modern and for one brief only. A per-project ledger (.layoza/looks.jsonl) records each dealt look, and every design-system / mechanics deal run prints a uniqueness block scoring nav, hero, sections, footer and motion against the last 20 runs (--window 1-200).

AI agents write front-end code quickly, but the result tends to look the same everywhere: cream and terracotta, Inter, three rounded cards, a purple gradient. They also break things they cannot see: a heading cut by the sticky header, a phone menu that Escape will not close, text at 3:1 contrast, a canvas that pushes LCP past 4 s.

Without LayozaWith Layoza
The same template for a law firm, a bakery and a SaaS appThree distinct art directions per brief, built from the trade's own objects (a tide chart for a fish restaurant, a till roll for a shop dashboard)
Restyles your existing site in its own tasteReads your site first (DESIGN.md, SITE-DNA.json) and extends it in your tokens, spacing and motion language
Animation hard-coded to one libraryPicks the lightest tool the brief needs (CSS, WAAPI, View Transitions, GSAP, Three.js), always with prefers-reduced-motion support and cleanup
"Looks good to me"Live Chromium QA at three widths with measured numbers; unmeasured values are reported as null, never guessed

Results

Six setups got the same one-line brief, the same model (Claude Opus 5.5) and one build agent each, and none could see the others' output:

SetupWhat it is
LayozaThis project
Claude frontend-designAnthropic's front-end design skill
impeccableOpen-source design skill
ui-ux-pro-maxOpen-source design skill
taste-skillOpen-source design skill
No skillPlain Claude, same prompt

A fresh blind judge then compared scroll stills at 1440 and 375 px for design, usability, creativity and content. Rival pages were frozen; only Layoza was rebuilt between rounds. Judge the pages yourself below.

Restaurant brief: a harbour seafood kitchen [Six restaurant homepages from the same brief, labelled Layoza, Claude frontend-design, impeccable, ui-ux-pro-max, taste-skill and No skill. Layoza's shows an illustrated boathouse at dusk and a crate of the day's catch]
Dashboard brief: a bakery chain's morning sales [Six bakery-chain sales dashboards from the same brief, labelled Layoza, Claude frontend-design, impeccable, ui-ux-pro-max, taste-skill and No skill. Layoza's uses a till-roll ledger and hourly bars]
Store brief: a small linen shop [Six linen-store homepages from the same brief, labelled Layoza, Claude frontend-design, impeccable, ui-ux-pro-max, taste-skill and No skill. Layoza's shows tea towels pegged on a washing line]
Kinetic agency brief: a motion-led studio homepage [Six kinetic agency hero sections from the same brief, labelled Layoza, Claude frontend-design, impeccable, ui-ux-pro-max, taste-skill and No skill, most with a 3D ribbon]
[The four Layoza pages at 390 px phone width]

Where Layoza does not win. Read this before you trust the pictures.

  • Kinetic is a tie, not a win. taste-skill's page was as strong there; across repeated rounds the lead changed hands and stayed inside judge noise.
  • Older single-brief rounds: impeccable beat Layoza on a simple page with no animation, and ui-ux-pro-max beat it in an earlier kinetic round.
  • One judge per round, judging screenshots. Motion itself is not judged, which is why the video uses real browser recordings.
  • Weak spots judges keep naming:
    • creativity on kinetic pages is merely good, not striking
    • headings that look cut by the sticky header in mid-scroll stills
    • small hero art on phones
    • a 3D hero whose lab LCP is well over the 2.5 s target

Full method, every round and the judge notes (with the raw scores) are in docs/CROSS-TYPE-BENCHMARK-2026-10.md. The demo pages were removed in October 2026 ahead of a fresh set. To run the QA on any page:

bash
npx layoza qa path/to/index.html

What it does

What you getHow
Layout expertAn industry read of the brief, 0–10 design dials, and three art directions that differ in layout, type, colour, content treatment and motionlayoza design-system "<brief>" · MCP get_design_system, recommend_layout
Site DNAFor an existing site: its tokens, type scale, spacing, components and motion, written to DESIGN.md, BRAND.md, MOTION.md and SITE-DNA.jsonlayoza inspect . --write · MCP inspect_project, extract_site_dna, inspect_site
Motion mechanics71 hero, section and micro mechanics dealt per niche and intensity, so a law firm gets calm, legible motion and an agency gets a kinetic herolayoza mechanics deal "<brief>" · MCP deal_mechanics, recommend_animation
Visual QAHeadless Chromium at 1440 / 768 / 375 px checks per-element contrast, clipping, overlap, focus-not-obscured, the phone menu (opens, traps focus, Escape closes) plus craft critiques; speed diagnostics are optionallayoza qa <file-or-url> · MCP capture_screenshots, audit_accessibility, audit_performance, verify_functional
Safe changesA baseline before a redesign, a before/after comparison, and one-command rollbacklayoza baseline create, layoza verify . · MCP compare_before_after, safe_rollback

Output is written in the project's own stack:

  • React, Next.js, Astro, Vue, Nuxt, SvelteKit
  • plain HTML/CSS/JS
  • WordPress block themes (theme.json v3)
  • Elementor or Bricks JSON
  • Shopify Liquid

Four modes

ModeWhenFirst command
A · New siteBlank projectlayoza design-system "<brief>" --mode new
B · ExtendAdd a page or section to a live sitelayoza inspect . --write
C · ImproveFix design, usability or accessibility without changing the brandlayoza baseline create pre-improve → layoza audit .
D · RedesignNew creative direction, keeping content and functionlayoza baseline create pre-redesign

The layoza router skill picks the mode from your prompt, so you can simply ask the agent: "Add a pricing page that matches the rest of the site."

Which one do I need?

  • Starting from nothing → A. You get three different directions to choose from before any code is written.
  • The site already looks right and you need more of it → B. Layoza copies your look; it does not impose its own.
  • The site works but looks tired or fails accessibility → C.
  • You want a new look → D. A baseline is taken first, so you can roll back.

Install

You need Node.js 18 or newer. The npm package ships prebuilt binaries for Windows x64, macOS (Intel and Apple silicon) and Linux (x64 and arm64); on other platforms it compiles from source on first run, which needs Rust. Visual QA also needs Playwright:

bash
npm i -D playwright && npx playwright install chromium

Then, in your project:

bash
npx layoza init      # skills + MCP config for every agent it detectsnpx layoza doctor    # checks Node, Playwright and the MCP handshake

Or add the MCP server by hand:

Claude Code
bash
claude mcp add layoza -- npx -y -p layoza layoza-mcp

For the skills, copy skills/* into .claude/skills/, or run npx layoza init.

Cursor

.cursor/mcp.json

json
{ "mcpServers": { "layoza": { "command": "npx", "args": ["-y", "-p", "layoza", "layoza-mcp"] } } }
OpenAI Codex
bash
codex mcp add layoza -- npx -y -p layoza layoza-mcp
Windsurf

~/.codeium/windsurf/mcp_config.json

json
{ "mcpServers": { "layoza": { "command": "npx", "args": ["-y", "-p", "layoza", "layoza-mcp"] } } }
OpenCode

opencode.json

json
{ "mcp": { "layoza": { "type": "local", "command": ["npx", "-y", "-p", "layoza", "layoza-mcp"], "enabled": true } } }
Google Antigravity

npx layoza init copies the skills into .agents/skills/ and writes .agents/skills.json and the .agents/plugins/layoza plugin. See docs/ANTIGRAVITY-OPTIMIZATION.md.

MCP tools

ToolPurpose
inspect_project · extract_site_dna · inspect_site · discover_componentsRead an existing codebase or live URL into design tokens and a component inventory
get_design_system · recommend_layoutIndustry read, dials and three creative directions for a brief
deal_mechanics · get_mechanic · recommend_animationNiche-aware motion mechanics and animation recipes
capture_screenshots · audit_accessibility · audit_performance · verify_functionalLive Chromium QA at three widths
compare_before_after · safe_rollback · export_reportBaselines, regression checks and reports
check_deal_conformanceDoes the built page follow its dealt page shape (restraints, button, motif)
search_guidelines · get_guideline · recommend_chart · get_stack_notes · get_icon_guidanceBundled UX guidelines, chart picks, stack notes and icon guidance (read-only)

recommend_layout is deprecated and unlisted, so tools/list returns 24 tools.

CLI extras

  • layoza guidelines search "<query>" [--limit 1-50] and layoza guidelines get <id>: the same guideline search as the MCP tools (synonyms and stems included).
  • layoza chart "<data shape>" [--task "<task>"]: top three chart types with fallbacks.
  • --window N on design-system and mechanics deal sets how many ledger runs the uniqueness check compares (default 36, max 200); --no-ledger ignores the ledger.
  • layoza audit . --strict and layoza verify . --strict turn gate warnings (such as a new site with no recorded approval of its direction) into errors.
  • layoza qa <file> --full runs full visual checks at every width. Speed checks are off by default; request --performance separately. --allow a,b limits it to the named passes. The report lists mode, passes and skipped_passes.
  • layoza conform <file> --deal deal.json [--direction N] checks the built page against the page shape it was dealt (design-system --json output): every restraint rule, the button shape and the motif, measured in Chromium at 1440px and 390px. It prints PASS / FAIL / unknown with evidence and a 0-100 score, and exits 2 when a check fails. QA finds defects; conform finds drift from the deal.
  • Environment: LAYOZA_QA_TIMEOUT_SECS (browser QA timeout), LAYOZA_PLAYWRIGHT_DIR (where Playwright is installed), LAYOZA_QA_ENGINE=python (use the Python Playwright engine).

inspect_site fetches the pages you point it at. Treat everything it returns as untrusted data: Layoza never executes instructions found inside an inspected page.

Skills

Layoza ships 19 skills with progressive disclosure: the layoza router plus 18 specialists.

  • Workflows: layoza-new-website, layoza-extend-website, layoza-refine, layoza-redesign
  • Design: layoza-site-dna, layoza-design-system, layoza-art-direction, layoza-creative-direction
  • Building: layoza-components, layoza-product-ui, layoza-figma, layoza-wordpress
  • Motion: layoza-animations, layoza-threejs-webgl
  • Checks: layoza-accessibility, layoza-performance, layoza-visual-qa, layoza-discovery-audit

See docs/SKILLS-GUIDE.md.

Compared to other approaches

Pick the one that fits your work.

LayozaClaude frontend-design skillTypical prompt-only design skillNo skill
FormRust CLI + MCP server + 19 skillsOne skill fileSkill + style rules or dataPlain agent
Reads an existing site firstYes, writes SITE-DNA.jsonNoSometimesNo
Motion guidance76 mechanics dealt per nicheGuidelinesGuidelinesNone
Browser verificationChromium at 3 widths, measuredNoChecklist or rule scanNo
Baseline + rollbackYesNoNoNo
Setupnpx, prebuilt binaryCopy one filenpx or PythonNothing

When to skip Layoza:

  • a quick one-off mockup that will never ship (frontend-design is lighter)

FAQ

Does it force GSAP or Three.js on my project? No. Your prompt wins. Layoza picks the lightest tool the brief needs, and every recipe honours prefers-reduced-motion and cleans up on unmount.
Will it overwrite my design? Not in Mode B or C. It reads your tokens first, and layoza baseline create plus safe_rollback let you undo any change.
Is the benchmark fair? As fair as we could make it. Rivals were frozen, the judge was blind, and losses are published. The limits are listed above; one judge per round is the weakest part. Pull requests that add judges or briefs are welcome.

Docs

Installation · CLI · MCP · Skills · Motion recipes · Existing-site workflows · Example prompts · Architecture · Security · Troubleshooting · Benchmarks

Credits

Layoza adapts ideas, not files, from open-source design skills under Apache-2.0 and MIT licences. Attribution is in THIRD_PARTY_NOTICES.md.

License

MIT

Evidence-backed design workflow

The default MCP tool list exposes all 24 supported tools. get_design_system accepts brief_context to preserve the actual client subject, facts and pinned choices and returns three compositions even in its default brief. design_assets inventories/registers real images with provenance; import_design_tokens imports local DTCG/Figma Variables JSON with aliases and modes; review_design persists actual screenshot evidence and flags stale source/renders; compare_before_after can decode and compare supplied PNG screenshots. Performance diagnostics remain opt-in.

Source: README.md at commit 905bf6d

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

2
  1. v0.1.4LatestOct 18, 2026
  2. v0.1.3Oct 18, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts