TrailQuest AI
Pick a time, a mood and a place, get a short outdoor mission from a local model — then close the tab and go outside.
Project intro
TrailQuest AI wants you to close the app. You pick how much time you have (30 minutes, an hour, two hours), what you feel like doing (walking, photography, nature observation, hiking), your energy level, and where you are (park, garden, mountains, neighborhood, anywhere). A local open-weight model then writes you a short outdoor mission: a few simple tasks, an observation challenge, an optional photo idea, a phone rule, and a safety reminder. Then you tap I'm going out, and the app tells you to close the tab.
When you are back, a check-in screen lets you tick off what you did, add a note and a photo, and see how long you were out. It ends with a Mission complete card you can screenshot. The screen is used for about a minute at each end; the outing itself needs none. The model is Gemma (gemma4:latest), an open-weight model running locally through Ollama, which writes every mission; swapping models takes one environment variable. Missions and check-in notes are saved in the browser's localStorage, so you can close the tab, go outside, and find your mission waiting when you return.
Vibe-coded evidence, in the author's own words on DEV (11 October 2026): "I built this with Cursor. The full source and commit history are in the GitHub repo above." Note: the post's build-process line also says the author built it with Antigravity and saved the session with DevRelay, so the build involved both framings; aiTools records Cursor per the explicit My Agent Session sentence. GitHub stars: 0 at the 28 October 2026 check.
Honest limits, flagged for the publisher: this project has no public hosted demo. The repository's homepage field points to an ephemeral Cloudflare tunnel URL that was verified dead on 28 October 2026, so demoUrl here is the GitHub repository itself (the distribution and setup page), not a running app, following the install-page precedent for non-hosted projects. Running it needs a local Ollama setup with a Gemma model; the author ran it on a CPU-only laptop with about 8 GB of RAM, and notes that after setup it needs no internet, except that the Google Fonts stylesheet falls back to system fonts when offline.
Actions
Tech stack
Project info
- Project category
- Entertainment
- Project status
- Online
- Collaboration intent
- None