Trailhead: An Offline-First Outdoor Companion

Description and use

Trailhead is an offline‑first outdoor companion that recommends daily activities based on interests, weather, and season, using local AI and open data.

Problem

Users want an app that recommends outdoor activities without relying on internet or costly APIs, preserving privacy and zero running costs.

Outcome

Trailhead delivers an offline-first, privacy‑preserving outdoor recommendation with zero daily cost, using only open-source tools.

Workflow

• 1. User opens app and grants location
• 2. App queries local weather via TabPFN microservice
• 3. Gemma 3 generates a daily brief based on interests and weather
• 4. OpenStreetMap + OSRM compute route to nearby park
• 5. App reads brief aloud and displays route

Evidence

Trailhead is an offline-first outdoor companion. You open the app for 30 seconds. It tells you the absolute best thing to do outside today (based on your interests, the weather, and what's in season).

Source

We built Trailhead entirely on open-source, local AI tooling: Mastra, Ollama + Gemma 3, TabPFN, OpenStreetMap + OSRM.

Source

Our TabPFN microservice is particularly powerful here — it doesn't need to be retrained. It just looks at a tiny CSV of 2 years of local weather data and immediately gives calibrated probabilities for cold snaps, frost risk, and general outdoor comfort without any API calls.

Source