{"slug": "stuck-doctor", "title": "Stuck Doctor", "summary": "A developer built Stuck Doctor, a health-nudge web app for a friend who avoids seeing a doctor, using Google's open-weight Gemma model served through Ollama with a Gradio backend on Render and a static GitHub Pages front end. The app deliberately avoids diagnosis or medication advice, instead identifying why someone is stuck and offering one small first step, with English, Hindi and Bengali support and an MIT license.", "body_md": "*This is a submission for the [Hacktoberfest Weekend Challenge: Build for a Friend](https://dev.to/challenges/hacktoberfest-weekend-2026-10-01)*\n\nI built Stuck Doctor for my friend Piku, who hesitates a lot before going to the doctor whenever she faces a health issue.\n\nWatching a friend put it off made me realize that waiting isn't laziness. It's usually fear, worry about money, awkwardness, not knowing where to start, or not knowing what to say. So instead of trying to replace a doctor, Stuck Doctor figures out why someone is stuck and gives them **one tiny first step**.\n\nWhat it does:\n\nIt deliberately does **not** diagnose, suggest medicines or doses, or read scans. It's a nudge, not a doctor.\n\nLive app: \n\n[https://kk-dev0.github.io/Stuck_Doctor/](https://kk-dev0.github.io/Stuck_Doctor/)\n\n(The AI backend may take a short while to wake up on the first visit.)\n\n[https://github.com/KK-Dev0/Stuck_Doctor](https://github.com/KK-Dev0/Stuck_Doctor)\n\nMIT licensed.\n\nThe AI engine is **Gemma**, Google's open-weight model family, run with **Ollama**. The backend uses **Gradio** and is hosted on **Render**, with a static front end on GitHub Pages. I built it in one day at Hacktoberfest 2026.\n\nGemma handles the language-heavy parts: understanding why someone is avoiding care, writing the first-step suggestion, playing Meera in the call rehearsal, writing messages for friends and family, explaining report values, and summarizing the doctor's instructions. It also lets the app respond in English, Hindi and Bengali.\n\nI added safety limits on purpose: the app never diagnoses or recommends medicines, summaries use only what the user wrote, report values are compared with the ranges printed on the report, and there's an optional \"double-check\" mode that reads a photo a second time. Emergency help is always one tap away. AI assistance was used in building this project, which is also disclosed on the site.\n\nA health tool for people who are already worried about money and access shouldn't depend on a paid API that could change its price or rules.\n\nAn open-weight model made it possible to build something this wide in a single day, support Indian languages, and keep the code open under the MIT license so others can fork it, translate it or improve its safety. It fits the theme perfectly: AI belongs to everyone, including the friend who has been too nervous, too busy or too broke to see a doctor.", "url": "https://wpnews.pro/news/stuck-doctor", "canonical_source": "https://dev.to/piks_dev/stuck-doctor-362f", "published_at": "2026-10-04 17:33:38+00:00", "updated_at": "2026-10-04 17:42:34.737362+00:00", "lang": "en", "topics": ["ai-products", "ai-tools", "large-language-models", "generative-ai"], "entities": ["Stuck Doctor", "Gemma", "Ollama", "Gradio", "Render", "GitHub Pages", "Google", "Hacktoberfest"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/stuck-doctor", "markdown": "https://wpnews.pro/news/stuck-doctor.md", "text": "https://wpnews.pro/news/stuck-doctor.txt", "jsonld": "https://wpnews.pro/news/stuck-doctor.jsonld"}}