Your AI Shopping Assistant with a Digital Memory

StyleMemory is a Chrome extension that transforms online fashion shopping by giving you a photographic memory for your wardrobe. Never buy duplicate clothes again — powered by semantic AI that understands "dark pullover" = "black hoodie".

• Add items you own to Supermemory (e.g., "black hoodie", "blue denim shorts")
• When you search for similar items → AI warns you: "You already own something similar!"
• Uses semantic understanding, not dumb string matching
• Manage wardrobe via extension OR directly in Supermemory dashboard

• Search across ALL retailers (H&M, Zara, Amazon, ASOS, etc.) from one place
• AI-powered query parsing extracts your style, budget, and preferences
• Learns your taste: avoid colors, preferred brands, budget limits

• Upload your photo once → try on any item instantly
• Powered by HuggingFace's IDM-VTON diffusion model
• See before you buy — reduce returns

• Add items from multiple retailers to one cart
• One-click checkout across all stores
• Auto-fills shipping info on retailer pages

1. Clone the repo:

   git clone https://github.com/yourusername/stylememory.git
   cd stylememory

2. Install dependencies:

   cd server
   npm install

3. Set up environment variables: Create a server/.env file:

   SUPERMEMORY_API_KEY=your_key_here
   GROQ_API_KEY=your_key_here
   SERP_API_KEY=your_key_here
   HF_TOKEN=your_key_here
   MEMORY_BACKEND=supermemory

   Get API keys:

   • Supermemory.ai - Digital memory storage
   • Groq - Fast LLM inference
   • SerpAPI - Shopping search
   • HuggingFace - Virtual try-on

4. Start the server:

   cd server
   node index.js

   Server runs at http://localhost:3456

5. Load the Chrome extension:

   • Open Chrome → chrome://extensions
   • Enable "Developer mode"
   • Click "Load unpacked"
   • Select the extension/ folder

// User adds to wardrobe via extension or Supermemory:
"black hoodie"

// User searches for:
"white oversized hoodie"

// Supermemory semantic search finds similarity:
Match: "black hoodie" (69% similarity)

// StyleMemory shows warning:
"⚠️ You already own something similar: black hoodie"

┌─────────────────┐
│ Chrome Extension│  (Sidepanel UI + Content Scripts)
└────────┬────────┘
         │
         ▼
┌─────────────────┐
│  Node.js Server │  (Express.js API)
└────────┬────────┘
         │
    ┌────┴────┐
    ▼         ▼
┌─────────┐ ┌──────────────┐
│Supermemory│ │  Groq LLM   │
│ (Wardrobe)│ │(Query Parser)│
└─────────┘ └──────────────┘

• Frontend: Chrome Extension (Manifest V3), HTML/CSS/JavaScript
• Backend: Node.js, Express.js
• AI:
  • Supermemory.ai - Semantic memory storage & hybrid search
  • Groq - LLM-powered query parsing (DeepSeek-R1)
  • HuggingFace IDM-VTON - Virtual try-on diffusion model
• APIs: SerpAPI (shopping search)

StyleMemory/
├── extension/           # Chrome extension files
│   ├── manifest.json
│   ├── sidepanel.html
│   ├── sidepanel.js
│   ├── background.js
│   └── content-scripts/ # Site-specific scrapers
├── server/              # Backend API
│   ├── index.js
│   ├── routes/          # API endpoints
│   │   ├── search.js
│   │   ├── wardrobe.js
│   │   ├── checkout.js
│   │   └── tryon.js
│   └── services/
│       ├── SupermemoryAdapter.js
│       └── MemoryAdapter.js
└── .env                 # API keys (gitignored)

Coming soon! Upload a demo video showing:

1. Adding wardrobe items to Supermemory
2. Searching for similar items
3. AI warning banner appearing
4. Virtual try-on
5. Multi-retailer checkout

This is a hackathon project, but contributions are welcome!

1. Fork the repo
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Commit changes (git commit -m 'Add amazing feature')
4. Push to branch (git push origin feature/amazing-feature)
5. Open a Pull Request

MIT License - feel free to use this for your own projects!

• Supermemory.ai - For the amazing semantic memory API
• Groq - For blazing-fast LLM inference
• HuggingFace - For the IDM-VTON virtual try-on model
• SerpAPI - For aggregated shopping search

Built for [Hackathon Name] by [Your Team]

• GitHub: @yourusername
• Email: your.email@example.com

⭐ Star this repo if you find it useful!