Homestagr
Homestagr is an AI assistant that helps real estate agents enhance property photos, write platform-specific listings, and generate fly-through videos — all through WhatsApp or a web interface.
The problem
Real estate agents waste hours editing photos and writing the same listing for different platforms. The goal was one conversation where they send photos and get back everything ready to publish. That “one conversation” constraint pushed me toward a single-agent architecture with tool-calling — one LLM (OpenAI Responses API) that orchestrates tools, routing between Gemini for image enhancement, Replicate/Kling for video generation, and Supabase for storage and state.
The hard part
The hardest part was WhatsApp. Messages arrive as separate webhooks with no grouping, so I built a batch accumulator in Redis with settling logic — the system waits a few seconds until photos stop arriving, drains them atomically, classifies each to reject non-property images, and only then spends credits on enhancement.
The stack
I built it on FastAPI backend with async workers (ARQ + Redis), Next.js frontend, Supabase (auth, database, storage), Stripe for credit-based monetization, and WhatsApp Cloud API integration. Deployed on DigitalOcean with GitHub Actions CI/CD. I also did the design. The cartoonish feel and yellow palette settled in after watching a few new Simpsons episodes — it fit real estate better than I expected.