OutsideIn: Turning AI-Powered Curiosity into Real-World Adventures
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass What if AI's most useful output wasn't another answer on your screen, but a reason to step away from it? We have built AI tools that write, summarise, code, plan, and answer almost any question. But what if we used AI to help us spend a little less time looking at screens? That question led me to build…
OutsideIn is a local-first nature exploration companion designed to help users spend less time on screens and more time outdoors. Built as part of the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass, OutsideIn uses AI to suggest things to observe in a garden, park, college campus, or neighborhood, encouraging people to notice the world around them.
The app allows users to choose where they are exploring, how much time they have, and what catches their curiosity, such as plants, biodiversity, sounds, or mindful observation. Once a quest is generated, the user follows practical steps, reflects on their experience, and receives a safety reminder. Observations can be recorded in a personal journal, creating a collection of moments from the world outside.
OutsideIn combines a React frontend, a Python backend, and local AI inference, using technologies like React and Vite, FastAPI and Uvicorn, Ollama for local AI inference, and Gemma-compatible open-weight models for nature-quest generation. Using open-weight AI supports privacy-conscious design, flexibility in experimenting with different model sizes, low running costs, and graceful degradation when AI is unavailable.
Building OutsideIn taught valuable lessons about validating requests, handling model failures, saving observations, and communicating loading and error states clearly.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
