TrailBuddy: less scrolling, more fresh air

Description and use

TrailBuddy simplifies choosing outdoor activities by offering three AI-generated ideas based on user input, using a local Qwen 2.5 3B model via Ollama.

Problem

Deciding what to do when you have a free hour and want to get outside can take longer than the walk itself.

Outcome

TrailBuddy streamlines the decision process for quick outdoor outings by providing concise, AI-generated activity suggestions without requiring internet connectivity after initial setup.

Workflow

• 1. User opens TrailBuddy web app.
• 2. User enters starting area, available time, and activity preference.
• 3. App sends request to local Ollama instance running Qwen 2.5 3B.
• 4. Ollama generates three activity ideas, rough duration, and one item to bring.
• 5. App displays the suggestions to the user.
• 6. User selects an idea and closes the tab, ready to go out.

Evidence

I made TrailBuddy. You put in a starting area, how much time you have, and what you feel like doing. It gives you three ideas, a rough duration, and one thing to bring.

Source

TrailBuddy is set up to use Qwen 2.5 3B through Ollama on your own machine. With the model downloaded and Ollama running, your request goes to the local Ollama endpoint rather than a hosted AI API.

Source

If Ollama isn't running, TrailBuddy falls back to a few built-in ideas and labels them as offline — those aren't AI-generated.

Source

I built the app with FastAPI and plain HTML, CSS, and JavaScript. It doesn't fetch maps, weather, or trail conditions, so the suggestions are ideas, not verified local recommendations.

Source