Want to touch grass but run out of options? Let Mochi the Explorer guide you to your next favourite spot!
Description and use
Mochi the Explorer automatically suggests 1–6 unique spots for short outings based on location, mood, and time, avoiding chain venues and highlighting independent places.
Problem
Locals in a city or town often lack fresh ideas for short outings and struggle to find unique, non‑chain spots that fit their mood and time constraints.
Outcome
Mochi the Explorer delivers personalized, non‑obvious outing suggestions in under a minute, improving local exploration and reducing reliance on chain venues.
Workflow
- 1. User inputs home location, mood, time available, and time of day.
- 2. Backend geocodes location via Nominatim.
- 3. Overpass API retrieves nearby places within a radius defined by duration.
- 4. Candidate places are filtered by tier (independent, landmark, chain) and tag diversity.
- 5. Gemma 4 selects and explains suitable spots, returning IDs.
- 6. Server resolves IDs to real names and coordinates.
- 7. Frontend renders map with Leaflet and pixel sprite via NES.css.
- 8. User receives recommendations and can navigate to suggested spots.
Evidence
All you have to do is tell Mochi where you live, what mood you're in, how much time you have and what time of day you're planning to head out and she'll plan the perfect outing for you!
Gemma is not allowed to come up with place names by itself. Each relevant candidate gets an ID (P1, P2...), Gemma answers with IDs, and my code looks up the real name and coordinates.
OpenStreetMap doesn’t record popularity, so I ranked places in tiers this way: independent places first, well‑documented landmarks next, and chains last.
- Record date: 2026-10-11T18:56:25.259Z