# OmniGuard AI > Source: > Published: 2026-10-04 14:38:33+00:00 *This is a submission for the [Hacktoberfest Weekend Challenge: Build for a Friend and Family](https://dev.to/challenges/hacktoberfest-weekend-2026-10-01)* What I Built I built OmniGuard AI — a free tool that detects scams, phishing messages, and fake UPI requests. I made it for my parents and grandparents. They keep getting fake WhatsApp messages like "Your bank account is blocked, click here." They never know if it's real. Now they just paste the message and OmniGuard AI tells them instantly — is it safe or a scam, and what to do next. It works in 10 languages including Hindi and Marathi. 🇮🇳 Demo 🔗 [https://kavach-web-2mkc.onrender.com](https://kavach-web-2mkc.onrender.com) Code OmniGuard AI is an open-source fraud detection and cyber defense platform. It is designed to identify and neutralize social engineering attacks, phishing, and financial fraud across digital channels. [Features](https://github.com/Anurag-tech22/DEV1#features) • [Architecture](https://github.com/Anurag-tech22/DEV1#architecture) • [Installation](https://github.com/Anurag-tech22/DEV1#installation) • [API](https://github.com/Anurag-tech22/DEV1#api) • [Contributing](https://github.com/Anurag-tech22/DEV1/CONTRIBUTING.md) • [License](https://github.com/Anurag-tech22/DEV1/LICENSE) How I Built It Backend: FastAPI (Python) with a custom scam detection rule engine AI: OpenAI GPT API for human-readable threat explanations Frontend: React 19 + Vite with a message scanner, threat radar, practice mode, and downloadable threat report Deployed on Render using Docker — single container serving both frontend and backend Why Does Open Innovation Matter? My family cannot afford a paid security product. With open source, I built something completely free that anyone in India can use. No subscriptions, no black box — you can see exactly why something was flagged, which builds trust with non-tech users. Prize Categories 🏆 Render — Best Use of Render