Hacktoberfest Weekend Challenge: Build for a Friend
What I Built 🧠 MindFlare: A Daily Brain Exercise App for My Mother I built MindFlare , a simple daily brain-exercise app for my mother. As our parents get older, it's normal to notice occasional forgetfulness, remembering a number, recalling a word, or keeping track of something they just saw. I wanted to build something that could turn a few minutes of everyday mental exercise into something…
The Hacktoberfest Weekend Challenge, "Build for a Friend", saw the creation of MindFlare - a simple daily brain exercise app designed specifically for the reporter's mother. The app focuses on short, enjoyable exercises such as mental math, memory recall, pattern puzzles, word memory, and visual memory. The interface is deliberately simple, with large buttons, readable text, minimal distractions, and encouraging feedback.
The app uses open-source AI through Ollama to generate new questions, memory exercises, pattern puzzles, and word-based challenges. This adds a personalized touch without relying on a closed AI API for every question. The AI can also adjust the difficulty of the challenges based on the user's performance.
MindFlare was built using a tech stack that includes HTML, CSS, JavaScript/React for the frontend, Python + FastAPI for the backend, and SQLite as the database. It is deployed on Render and its code is available on GitHub. The project emphasizes open innovation, allowing the reporter to experiment with different open-weight models, run them locally during development, control the prompts and generation process, and customize the AI behavior for the specific use case.
This personal project is especially meaningful to the reporter as it allows him to experiment with open AI technology in a way that feels less like "calling an AI API" and more like actually building with AI. The app is intended to make someone's everyday life a little better, which aligns with the spirit of Hacktoberfest #BuildForAFriend.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
