Skip to main content
Glama
deenesjakoruzh
sarveshsea

memoire

by sarveshsea
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Hybrid

Try it now

npx @sarveshsea/memoire design-doc https://stripe.com

Extracts colors, typography, spacing, shadows, and component patterns from any public URL. Outputs a DESIGN.md with a Tailwind config sketch. 10 seconds. Zero config.

What you get

Input

Output

Any public URL

DESIGN.md with full token inventory + Tailwind config

Figma file (REST or plugin)

Design tokens, components, styles

Penpot file

Same tokens, same pipeline

JSON specs

React + TypeScript + Tailwind components (shadcn/ui)

Generated components

Storybook stories + shadcn registry server

npm i -g @sarveshsea/memoire

memi design-doc https://linear.app     # extract any site's design system
memi go                                 # figma -> tokens -> specs -> components -> preview
memi go --rest                          # same thing, no figma desktop needed
memi go --penpot                        # same thing, from penpot
memi tokens                             # export as CSS / Tailwind / JSON / Style Dictionary

Use with Claude Code / Cursor

Memoire is an MCP server with 20 tools. Give your AI assistant direct access to your design system.

memi mcp config --install              # writes .mcp.json, done

Or add manually to .mcp.json:

{
  "mcpServers": {
    "memoire": {
      "command": "memi",
      "args": ["mcp", "start"]
    }
  }
}

Tools include: pull_design_system, generate_code, create_spec, get_tokens, compose, design_doc, run_audit, capture_screenshot, analyze_design, and 11 more.

Full command reference

Command

What it does

memi setup

Full onboarding: token, file, plugin, bridge, MCP config, test pull

memi init

Initialize workspace with starter specs

memi connect

Start Figma bridge (auto-discovers plugin on ports 9223-9232)

memi pull

Extract tokens, components, styles from Figma

memi pull --rest

Pull via REST API -- no plugin, no Figma Desktop

memi pull --penpot

Pull from Penpot (needs PENPOT_TOKEN + PENPOT_FILE_ID)

memi spec <type> <name>

Create a component, page, or dataviz spec

memi generate [name]

Generate shadcn/ui code + Storybook stories from specs

memi generate --no-stories

Generate without Storybook stories

memi preview

Start preview gallery + shadcn registry server

memi go

Full pipeline in one command

memi export

Export generated code into your project

memi tokens

Export tokens as CSS / Tailwind / JSON / Style Dictionary (W3C DTCG)

memi validate

Validate all specs against schemas

Command

What it does

memi design-doc <url>

Extract design system from any URL into DESIGN.md

memi design-doc <url> --spec

Also write a DesignSpec JSON for codegen

memi extract <url>

Alias for design-doc

Command

What it does

memi sync

Full sync: Figma + specs + code

memi sync --live

Watch and sync continuously

memi compose "<intent>"

Agent orchestrator: classify, plan, execute

memi agent spawn <role>

Spawn a persistent agent worker

memi research from-file <path>

Process Excel/CSV into research

memi research synthesize

Synthesize themes and personas

memi daemon start

Start daemon with reactive pipeline

Command

What it does

memi status

Project status overview

memi doctor

Health check: project, plugin, bridge

memi dashboard

Launch monitoring dashboard

memi audit

Design system audit (WCAG, unused specs)

All commands support --json for structured output.

Spec-first workflow

Every component starts as a JSON spec before code is generated:

{
  "name": "MetricCard",
  "type": "component",
  "level": "molecule",
  "shadcnBase": ["Card", "Badge"],
  "props": { "title": "string", "value": "string", "trend": "string?" },
  "variants": ["default", "compact"]
}

Specs are validated with Zod schemas. Components follow Atomic Design (atom, molecule, organism, template, page).

Architecture

src/
  engine/     Core orchestrator, registry, sync, pipeline
  figma/      WebSocket bridge + REST client + Penpot client
  agents/     Intent classifier, plan builder, task queue
  mcp/        MCP server (20 tools, 3 resources, stdio)
  codegen/    shadcn/ui mapper, Storybook, dataviz, pages
  research/   Research engine (Excel, stickies, web)
  specs/      Spec types, Zod schemas, 62-component catalog
  preview/    Preview gallery, API server, shadcn registry
  notes/      Downloadable skill packs
  commands/   28 CLI commands
  plugin/     Figma plugin (Widget V2)

Links

memoire.cv -- Changelog -- MCP docs -- Notes

License

MIT

Install Server
A
security – no known vulnerabilities
A
license - permissive license
A
quality - A tier

How are these scores calculated?

Resources

Tools

View all tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/sarveshsea/m-moire'

If you have feedback or need assistance with the MCP directory API, please join our Discord server