Branding Agent

Extract brand design systems from any website using Firecrawl, then use AI tools to export tokens, generate color palettes, check accessibility, and analyze brand personality.

Loading preview…

Problems solved

Technical challenges this implementation handles out of the box.

Extract brand design systems from a website with Firecrawl
Export brand tokens as CSS, Tailwind, or JSON
Generate palette variations and check WCAG contrast
Analyze brand personality and suggest component styles

Use cases

Products and workflows this pattern is designed to support.

Brand design system extraction
Design token handoff to engineering
Accessibility-minded palette exploration
Brand personality audits

Setup

Requirements, wiring steps, and what this pattern adds to your project.

Getting started

Pick how you want to pull this pattern in. Then wire env vars and routes the same way.

1
Download → Next.js app
Use Download → Next.js app in the preview toolbar. You get a zip scaffold (Pro downloads rewrite preview `/view/.../api/*` paths to `/api/*` automatically).
2
Extract the zip and install dependencies
Unzip the archive, then run `pnpm install` (or npm / yarn) in the project folder.
3
Fill .env.local
The download includes .env.local placeholders when needed. Add real values for: OPENAI_API_KEY, FIRECRAWL_API_KEY.
4
Customize the agent and tool files
Adapt prompts, tools, and stop conditions in the generated project for your product.
5
Run the app and open the pattern route
Run `pnpm dev`, open the setup/checklist page if present, then navigate to the generated pattern route and verify responses.

Environment variables

OPENAI_API_KEYGet key
FIRECRAWL_API_KEYGet key

Capabilities

AI SDK APIs

useChatgatewayToolLoopAgenttoolhasToolCallstepCountIscreateAgentUIStreamResponseInferAgentUIMessageDefaultChatTransportUIMessage

Providers

OpenAI

External services

FirecrawlUpstash

Files added

13 files

app/page.tsx
app/layout.tsx
app/api/branding-agent/route.ts
lib/actions.ts
lib/branding-types.ts
lib/rate-limit.ts
lib/ai/branding-agent.ts
lib/ai/tools/export-tokens.ts
lib/ai/tools/generate-palette.ts
lib/ai/tools/analyze-accessibility.ts
lib/ai/tools/generate-components.ts
lib/ai/tools/suggest-personality.ts
README.md

Dependencies

16 total

npm packages

AISDK@mendable/firecrawl-jsUpstashlucide-reactNext.jsReactsonnerZod

Registry components

alertbadgebuttoncardcollapsibleinputprogressskeleton

Critical files

branding-agent/route.ts
API route using createAgentUIStreamResponse with brandContext passed via callOptions.
ai/branding-agent.ts
ToolLoopAgent with callOptionsSchema + prepareCall that injects brand context into instructions and experimental_context. Uses stopWhen with hasToolCall for each tool.
tools/generate-palette.ts
Color palette generation tool with HSL color theory algorithms (shades, complementary, analogous, accessible). Most complex branding tool.
tools/analyze-accessibility.ts
WCAG contrast ratio analysis tool computing ratios between color pairs and evaluating AA/AAA compliance.
tools/export-tokens.ts
Design token export tool generating CSS variables, Tailwind config, or JSON design tokens.
tools/generate-components.ts
Component style generation tool creating styled examples from brand tokens.
tools/suggest-personality.ts
Brand personality suggestion tool analyzing colors and typography for tone and audience alignment.
lib/actions.ts
Server action for initial brand data extraction from a URL. Provides the brandContext that feeds into the agent.

Requirements

Complexity: Advanced
Setup time: ~10 minutes
Node: 24+
Memory: 256MB

Upstash Redis

Loading preview…

Branding Agent

Branding Agent

Problems solved

Use cases