This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass
What I Built
TrailScout creates copy-ready running and walking loop itineraries from your terminal.
It uses OpenStreetMap (OSM) walkable ways when online and can use a local GeoJSON file
when offline.
Demo
Code
TrailScout Web
TrailScout is a mobile-first walking-route planner for outdoor enthusiasts and run-club organizers. It turns an OpenStreetMap place search into an OSM-routed walking loop, highlights nearby mapped green spaces, and adds concise, deterministic route notes and low-friction challenge ideas.
Live app: trailscout-web-three.vercel.app
Built for the DEV Hacktoberfest Open-Source AI Challenge — Week 1 / Touch Grass theme. The route planner does not call a paid AI service: its current narrative engine is local, deterministic TypeScript. A typed adapter boundary is ready for a future local Gemma integration, but no model is downloaded or required.
Features
- Search for a park, neighborhood, or town; choose a 3 km, 5 km, 10 km, or custom 1–30 km target.
- Request actual pedestrian network routes from the OSM-based routing.openstreetmap.de foot router. Up to three real route candidates are ranked for target-distance fit and the selected green-space / quieter-road preferences; an unroutable candidate is…
How I Built It
I used Github Copilot to build it.
Why Does Open Innovation Matter?
The route data comes from a community-maintained open map rather than a proprietary routing subscription.
Prize Categories
~ Github Copilot
Thank You !!
Top comments (0)
Some comments may only be visible to logged-in visitors. Sign in to view all comments.