RESET-Return to What Matters
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass What I Built Re:Set is an open-source, open-weight AI experience designed to help people reclaim their attention from screen addiction and return to tactile offline life—starting with reading . We built AI that can write code and generate images; we wanted to build an AI whose sole purpose is to help people…
Reset is an open-source, open-weight AI experience aimed at helping people break their screen addiction and return to offline life. It goes beyond just generating code or images; instead, Re:Set focuses on creating a tactile, single-action offline ritual that helps users reclaim their attention and put down their phones.
The app begins with a low-friction spark, where users share their personal reasons for struggling to read and the amount of time they have available. Using Google's open-weight model Gemma 2, Re:Set generates a customized location rule, tactile anchor, and attention anchor for each user. This approach contrasts with other AI-powered productivity tools, which often trap users in endless loops and gamified dashboards.
Once the user clicks "Begin Re:Set," the application transforms into a serene, distraction-free interface, encouraging users to put their phones away. After returning, users are greeted with a non-judgmental reflection of their experience, without any streaks, guilt, or gamified penalties. Re:Set also offers community silent reading gatherings at local bookstores, libraries, and cafés, allowing attendees to participate in a private, privacy-preserving environment.
The 10-step experience flow includes expressing personal friction, receiving a customized challenge, transitioning offline, checking in at a venue, completing the session, reflecting on personal takeaways, and viewing cumulative offline time returned to real life. The app's architecture is built on React 18, Node.js, Express, Mongoose, Google Gemma 2, MongoDB Atlas, and custom Sentry observability.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
