About Wardrowbe

Wardrowbe is a wardrobe app that uses AI to help you organize your clothes and decide what to wear. You photograph your clothing, AI analyzes each item, and the app suggests outfits based on the weather, the occasion and your personal style.

It comes in two forms: Wardrowbe Cloud, a hosted service with iOS, Android and web apps, and an open source version you can run on your own server.

The project started from a simple frustration: standing in front of a full closet with nothing to wear. Existing wardrobe apps were either abandoned, locked behind paywalls with no way to self-host, or just not very good. Wardrowbe was built to be the tool we actually wanted to use.

The core of Wardrowbe is open source under the MIT License: the backend, the web app, AI tagging, outfit suggestions, weather, households, notifications and wardrobe analytics. Anyone can run it with Docker Compose, with no item caps and no license key.

Self-hosting keeps your data on your own server. You choose the AI provider (Ollama for local inference, OpenAI, or any OpenAI-compatible API), and it runs on anything that supports Docker: a Raspberry Pi, an old laptop, a NAS or a VPS.

Wardrowbe Cloud at app.wardrowbe.com adds features that depend on hosted infrastructure, business agreements or our developer accounts:

• The iOS and Android apps. Free to download, built and published by us, and not open source. They work with Wardrowbe Cloud and can also connect to your own server.
• Virtual try-on, which runs on rented GPUs.
• Partner store suggestions, which rely on our agreements with stores and affiliate networks.
• Sign in with Apple and Google, subscriptions and billing.
• Receipt import, adding items from a text description, and achievements, which we built for the cloud service.

Wardrowbe Cloud also takes care of hosting, AI tagging and updates, so there is nothing to install. Subscriptions are how Wardrowbe is paid for, and they fund the work on both versions.

1. Photograph your clothes — snap a photo of each item. The AI detects clothing type, color, pattern, fabric, and style automatically.
2. Get daily outfit suggestions — each morning, the app checks your local weather, analyzes your wardrobe, and suggests complete outfits tailored to your day.
3. Build your style profile — accept or skip suggestions and the AI learns your preferences over time. Discover which items you actually wear, find forgotten pieces, and make smarter decisions about your closet.

• Backend: FastAPI, PostgreSQL, Redis (task queue)
• Frontend: Next.js, TypeScript, TanStack Query
• Mobile: React Native (Expo) for iOS and Android
• AI: Any OpenAI-compatible API — Ollama, OpenAI, or your own
• Auth: any OIDC provider (PocketID, Keycloak and others); the cloud also offers Sign in with Apple and Google
• Deploy: Docker Compose (self-hosted) or Kubernetes (cloud)

The open source version is developed in the open. Bug reports, feature requests and pull requests are welcome on GitHub.