Outside Window: A Local AI Agent That Gets You Off the Screen
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass . What I Built Outside Window is a privacy-first personal agent that helps someone take one realistic outdoor break today. Most wellness apps turn going outside into another dashboard to manage. Outside Window takes the opposite approach: the screen should be the shortest part of the experience. The app gives…
This article is about an open-source AI project called "Outside Window," which aims to encourage users to take a short break outside the digital world. The app is a personal agent that promotes privacy and offers a gentle nudge for people who spend excessive time online. The core features include a recommended time window, a ten-minute outdoor micro-quest, a check-in system, and a log of user outings.
The application uses the Gemma language model from Ollama for local inference, allowing users to run the app offline if desired. Data is stored locally using SQLite, and the outing history can be exported as CSV. The project emphasizes transparency, allowing users to inspect the recommendation process and data collection methods.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
