#8484th of 107 in Coding agents and AI editors
design-extract
CLI that extracts a website's design system into tokens, Tailwind and Figma files
Live demo ↗
(opens in a new tab)Website ↗
(opens in a new tab)Repository on GitHub ↗
(opens in a new tab)
- Stars
- 4.3k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Sep 2026
- Language
- HTML
1 on 14 Apr 20264,278 on 20 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
designlang drives a headless Chromium against a URL and reads colors, type, spacing, layout, motion and component structure from the live DOM. It writes 17+ files, including W3C DTCG tokens, a Tailwind config, a shadcn theme, Figma variables and prompt packs for v0, Lovable and Cursor. It also covers site-wide crawls, clone fidelity scoring, drift checks, a Claude Code plugin and a stdio MCP server.
Who it is for: Frontend developers and designers who extract or clone site design systems
Strengths
- Emits many formats per run: DTCG, Tailwind, shadcn CSS, Figma variables, typed React stubs
- Measures clones with pixel diff plus motion comparison, with a --min flag usable as a CI gate
- Ships a Claude Code plugin and an MCP server (designlang mcp) for agent use
- Core extraction runs locally and deterministically; the API key is only needed for --smart
Weaknesses
- Needs a separate Chromium download via install-browser, or an installed Google Chrome
- Authenticated pages need cookies or headers passed by hand
- The README lists a very large command surface, which makes it hard to know where to start
- --smart classification needs an external OpenAI-compatible or Anthropic API key
What it needs
- no GPU
- Docker
- Needs Node.js, Chromium via Playwright or Google Chrome, Optional: Atlas Cloud, OpenAI or Anthropic API key for --smart
- Models: OpenAI-compatible chat API (Atlas Cloud), OpenAI, Anthropic
Also in Coding agents and AI editors
See all 107| Rank | Project | Score |
|---|---|---|
| 1 | claw-codeRust CLI coding agent harness using Anthropic and OpenAI-compatible APIs | 83 out of 100 |
| 2 | ArchonYAML workflow engine that runs AI coding agents through fixed dev steps | 83 out of 100 |
| 3 | Open SWEAgent that turns issues into pull requests, reviews PRs and monitors CI | 81 out of 100 |
| #4 | oh-my-openagentTerminal coding agent with multi-model orchestration and git-backed memory | 80 out of 100 |
| #5 | gooseRust AI agent with desktop app, CLI and API, extended through MCP | 80 out of 100 |