Layoza
io.github.layoza由 GitHub 帳號 layoza 發布v0.1.4更新於 Nov 2, 2026
Design systems, layout and motion guidance for AI agents, plus headless Chromium visual QA.
概覽
Layoza 為助理提供設計系統、版面與動效指引,並以無頭 Chromium 對頁面做視覺品檢。
- 可以做什麼
- 讀取程式碼庫或線上網站,萃取設計權杖、網站 DNA 與元件清單
- 針對需求給出產業解讀、設計刻度與三個不同的創意方向
- 依細分產業派發動效機制與動畫方案
- 在三種寬度下以無頭 Chromium 進行截圖、無障礙、效能與功能檢查
- 建立基準、比對修改前後、回復並匯出報告
- 檢索內建的 UX 指南、圖表選擇、技術棧說明與圖示建議
- 適用情境
- 適合助理撰寫或改版前端頁面、且希望產出遵循一致設計方向並在真實瀏覽器中驗證的情況。可用於新建網站、擴充現有網站、無障礙與可用性修正,以及具回復機制的改版。
- 執行需求
- 透過 npx 以 stdio 本機程序執行,需要 Node.js 18 或更新版本。預編譯二進位檔涵蓋 Windows x64、macOS 與 Linux x64/arm64,其他平台首次執行需從原始碼編譯並依賴 Rust。視覺品檢另需安裝 Playwright 與 Chromium。可選環境變數可設定品檢逾時、Playwright 路徑與引擎。
安裝
在 SourceWeft 中
- 開啟 儀表板中的 Layoza,將其新增到工作區。
- 為需要使用其工具的對話啟用該服務。
Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。
其他 MCP 客戶端
參照 儲存庫 中的啟動說明。
README
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]▶ Download the full 2½-minute showcase (MP4, 17 MB): all four briefs, recorded live in Chromium
Then just talk to your agent. Example prompts:
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.
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:
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]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:
What it does
Output is written in the project's own stack:
- React, Next.js, Astro, Vue, Nuxt, SvelteKit
- plain HTML/CSS/JS
- WordPress block themes (
theme.jsonv3) - Elementor or Bricks JSON
- Shopify Liquid
Four modes
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:
Then, in your project:
Or add the MCP server by hand:
Claude Code
For the skills, copy skills/* into .claude/skills/, or run npx layoza init.
Cursor
.cursor/mcp.json
OpenAI Codex
Windsurf
~/.codeium/windsurf/mcp_config.json
OpenCode
opencode.json
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
recommend_layout is deprecated and unlisted, so tools/list returns 24 tools.
CLI extras
layoza guidelines search "<query>" [--limit 1-50]andlayoza 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 Nondesign-systemandmechanics dealsets how many ledger runs the uniqueness check compares (default 36, max 200);--no-ledgerignores the ledger.layoza audit . --strictandlayoza verify . --strictturn gate warnings (such as a new site with no recorded approval of its direction) into errors.layoza qa <file> --fullruns full visual checks at every width. Speed checks are off by default; request--performanceseparately.--allow a,blimits it to the named passes. The report listsmode,passesandskipped_passes.layoza conform <file> --deal deal.json [--direction N]checks the built page against the page shape it was dealt (design-system --jsonoutput): 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;conformfinds 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.
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 honoursprefers-reduced-motion and cleans up on unmount.
Will it overwrite my design?
Not in Mode B or C. It reads your tokens first, andlayoza 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.
來源:README.md,提交 905bf6d
工具
0版本歷史
2- v0.1.4最新Oct 18, 2026
- v0.1.3Oct 18, 2026
評分
已滿足適用檢查項的 50%
該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。
- 近 30 天內可連通25 分
請保持端點能夠回應 MCP 握手;SourceWeft 每 30 天探測一次。
- 已宣告認證方式10 分
請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。
- 已列出工具15 分
請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。
- 描述必需15 分
- 圖示10 分
- 文件15 分
- 授權條款10 分