Show HN: Marque – MCP/CLI server for persistent agent design identity(marque-web.vercel.app)
marque-web.vercel.app
Show HN: Marque – MCP/CLI server for persistent agent design identity
https://marque-web.vercel.app/
4 comments
The "agent starts from zero" problem Marque addresses is one of the most frustrating aspects of working with AI coding agents at scale. Every new conversation, the agent has no memory of your color palette, your spacing system, your component patterns, or the reasoning behind your design decisions. You end up spending 30% of every prompt re-establishing context that should be ambient.
Moving design identity to the infrastructure level rather than the prompt level is the right architectural instinct. When `get_design_context_for()` is a first-class call the agent makes before writing any component, the design system becomes a constraint the agent generates within rather than a suggestion it can ignore.
This maps directly to the Agile Vibe Coding Manifesto's principle that "architecture guides and constrains generation." The manifesto's argument is that system-level constraints — including design systems, API contracts, and architectural conventions — should be explicit inputs to generation rather than things developers have to re-inject into every prompt.
The "marque improve" drift detection loop is clever: https://agilevibecoding.org
Moving design identity to the infrastructure level rather than the prompt level is the right architectural instinct. When `get_design_context_for()` is a first-class call the agent makes before writing any component, the design system becomes a constraint the agent generates within rather than a suggestion it can ignore.
This maps directly to the Agile Vibe Coding Manifesto's principle that "architecture guides and constrains generation." The manifesto's argument is that system-level constraints — including design systems, API contracts, and architectural conventions — should be explicit inputs to generation rather than things developers have to re-inject into every prompt.
The "marque improve" drift detection loop is clever: https://agilevibecoding.org
I'm also curious for what everyone else's workaround for generic UI, like how do you handle it currently and why that method specifically?
Honestly, I've moved away from trying to heavily customize 'off-the-shelf' UI libraries to fight the generic look. Instead, I’m using a 'Headless + Tokens' approach. For data-heavy, generic-looking layouts (tables/forms), I am leaning into Generic TS Components. I'm also focusing on 'Progressive Reduction' of UI. I'm very impressed with your progress as a high school pupil. I wish you the best of luck in your future endeavors! Keep me posted!
That is what Marque is.
npm install -g marque-cli marque stamp stripe.com marque synthesize --apply marque mcp setup
marque synthesize turns that into an actionable mark: a concept philosophy with a core metaphor, a pattern vocabulary with JSX blueprints, anti-defaults telling the agent exactly what not to build, and section guidance per page type.
marque mcp setup writes config files for Claude Code, Cursor, Copilot, Windsurf, Codex, and Antigravity simultaneously. The agent calls get_design_context_for() before it writes a single line.
Real design taste is never singular though. Kirby Ferguson's Everything is a Remix maps directly here: the best design is copy, transform, combine. marque blend lets you pass multiple references with weights, scrapes them in parallel, interpolates the typography scale numerically, resolves color dominance by weight, and synthesizes a concept philosophy describing the creative tension between the references as a named design identity. Not averaging two sites. Creating something original from the intersection of what you admire.
marque blend lusion.co vercel.com 0.6 0.4
And once the agent starts building, marque improve keeps it honest. Agents drift. By the third component they are back to generic defaults. The improve loop screenshots your running dev server, diffs it against your mark using a vision model, writes element level violations by severity to a corrections file, and re-scores on every file change until the output actually matches.
marque improve --url localhost:3000 --target 85
The goal is simple: vibe-coded products should look as good as they build fast. Everything is free and open source.
Demo: https://www.youtube.com/watch?v=DB8VvzUxtvY
GitHub: https://github.com/parthsharma234/marque-cli
Looking for some feedback and any comments/concerns.