DogeVault Stylist — AI Dog Fashion Stylist

A developer built DogeVault Stylist, a Next.js app that turns a single dog photo into a shopping experience, using AI to enhance the image, generate a profile, fetch real products via Apify MCP, and approve budget-limited USDC transfers on Solana devnet. The app chains six providers, including YouCam, Gemini, and ElevenLabs, with graceful degradation for missing keys, and includes a custom hybrid virtual try-on for dogs since YouCam's API is human-only.

This is a submission for Weekend Challenge: Dog Days Edition DogeVault Stylist is a Next.js app that turns a single photo of your dog into a full shopping experience. You upload a dog photo, and the app: The goal was to build something that feels like a real product — not a demo with hardcoded data. Every product card links to a live listing. Every transaction hits Solana devnet. Every voice line is synthesized. Video demo placeholder — upload and link your demo video here AI dog stylist + autonomous shopper for the Dog Days hackathon. Upload a dog photo, get a YouCam studio portrait, hear an ElevenLabs stylist reaction, fetch real products through Apify MCP, and approve a budget-limited USDC transfer on Solana devnet. apps/web programs/doge vault apify/e-commerce-scraping-tool apps/web Next.js app src/lib Server/client libraries src/app/api/agent Upload - YouCam - Gemini - Apify orchestration src/app/api/voice ElevenLabs text-to-speech src/components DogeVault UI and Solana wallet flows programs/doge vault Anchor vault program PLAN.md Full hackathon plan and decisions Copy .env.example to .env and fill in keys. Important values already configured for devnet: The repo is a pnpm monorepo: apps/web — Next.js 16 frontend and API routes programs/doge vault — Anchor 0.32.1 Solana program adk-apify-sample/ — Standalone Google ADK agent Python Everything starts with one API call to /api/agent . The server-side orchestrator chains six providers in sequence, streaming progress back to the UI via SSE: Upload → YouCam enhance → YouCam background replace → Gemini profile → Apify product search → Virtual try-on → ElevenLabs voice Each step is isolated in its own module under apps/web/src/lib/ , so a missing API key degrades gracefully instead of crashing the whole pipeline. The UI shows a status badge per provider ok / missing key / error . This was the hardest part to get right. The Apify MCP server https://docs.apify.com/integrations/mcp solved my product extraction problem. It exposes Apify Actors as tools over the Model Context Protocol. I call the apify/e-commerce-scraping-tool Actor from my Next.js backend using the official MCP TypeScript SDK: js const client = new Client { name: "dogevault-stylist", version: "0.1.0" } ; const transport = new StreamableHTTPClientTransport new URL "https://mcp.apify.com/?tools=apify/e-commerce-scraping-tool,get-actor-run,get-dataset-items" , { requestInit: { headers: { Authorization: Bearer ${APIFY TOKEN} } } } ; await client.connect transport ; Actor runs are async — the server returns a runId , and I poll get-actor-run until SUCCEEDED , then read get-dataset-items . The whole flow returns normalized product cards with images, prices, ratings, and direct URLs from Amazon, eBay, and other marketplaces. Gemini handles three jobs: The profile also tags the subject as dog or human , which determines which virtual try-on path the app takes downstream. YouCam's virtual try-on API is human-only I just knew about it during development — it works great for clothes, hats, and shoes on people, but can't dress a dog. So I built a hybrid: cloth-v3 , hat , shoes with the Apify product image as the garment reference. qwen-image-3.0-pro edits the dog portrait to wear the selected product, using both the dog photo and product image as references.The stylist script from Gemini gets sent to ElevenLabs for text-to-speech. One gotcha: free ElevenLabs plans can't use library voices via the API returns HTTP 402 paid plan required . The app catches this and falls back to the browser's built-in SpeechSynthesis — so the feature still works, just with a less polished voice. The on-chain piece is an Anchor program that acts as a spending guardrail: initialize vault approve spend This means even if the AI recommends a $500 Gucci dog collar, the vault won't let it through. After approval, the app mints a compressed NFT cNFT via Metaplex Bubblegum V2 as a receipt — containing the portrait, try-on image, product details, and transaction reference. Best Use of ElevenLabs — The AI stylist's reaction script generated by Gemini is converted to speech via the ElevenLabs text-to-speech API. The app handles the free-plan 402 error gracefully, falling back to browser SpeechSynthesis so the voice feature always works. Best Use of Google AI — Gemini powers three core features: dog breed/style profiling from the uploaded photo, stylist script generation for the voice reaction, and product search query planning that feeds the Apify scraper. Gemini is the decision-making layer that ties the entire pipeline together.