Five-Minute Field Notes: a local Gemma card that sends me outdoors

A developer built Five-Minute Field Notes, a local app that uses Google's open-weight Gemma 3 1B model via Ollama to generate three short observation cues and a reflection question for a five-, ten-, or fifteen-minute outing to a nearby park, garden, or balcony. The app runs entirely on a Mac with Python's standard library and no cloud keys or package dependencies, sending four fixed choices from the browser to a local server that validates the model's structured JSON card before displaying a printable version. The developer notes that the 1B model sometimes produces repetitive cues and that the app validates structure but not whether suggestions fit a real place.

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass https://dev.to/challenges/hacktoberfest-week1-2026-10-05 Five-Minute Field Notes makes a tiny observation mission for a place I can already access: a park, garden, quiet sidewalk, campus, or balcony. I select what I want to notice, whether I will stroll or stay seated, and whether I have 5, 10, or 15 minutes. A local model creates three short cues and a question for when I return. The useful part happens after I close the page and go outside. I deliberately skipped maps, live weather, and species identification. The app cannot know which route is safe or what wildlife will appear. It gives me a way to pay attention where I already am. This is a solo submission. There are no teammates to credit. Watch the 31-second silent demo https://github.com/kvianAR/five-minute-field-notes/blob/main/demo/five-minute-field-notes-demo.mp4 . It shows the running app, my selections, the local model generating a card, and the finished printable card. There is no voice or music. My quick demo path is Balcony or doorstep → Sounds → From one seated spot → 5 minutes → Make my field card. The resulting card is generated by gemma3:1b on my Mac. I can print it, put the screen away, and follow the cues from one safe spot. Public GitHub repository https://github.com/kvianAR/five-minute-field-notes · Setup instructions https://github.com/kvianAR/five-minute-field-notes run-on-a-mac · Build notes and verification https://github.com/kvianAR/five-minute-field-notes/blob/main/BUILD NOTES.md The complete app has two main files: app.py is the local Python server and Ollama call, and index.html is the responsive interface and printable card. README.md has setup instructions and the demo flow; tests.py checks the model request and card validation. It runs with Python's standard library, Ollama, and the small Gemma 3 model. There are no cloud keys or Python package dependencies for the app. To run it on a Mac, install Ollama, then run: git clone https://github.com/kvianAR/five-minute-field-notes.git https://github.com/kvianAR/five-minute-field-notes.git cd five-minute-field-notes ollama pull gemma3:1b python3 app.py Open http://127.0.0.1:8765 http://127.0.0.1:8765 in a browser. Downloading the model needs internet once; afterward, generation runs locally. The browser sends four fixed choices to a Python server running on 127.0.0.1. The server asks local Ollama to run Google's open-weight Gemma 3 1B model. Gemma writes the three observation cues and reflection question as structured JSON. The server checks that the card is complete; the browser displays the text safely and offers a printable version. AI is the core of this project: without Gemma's generated cues, there is no field card. The model combines the selected place, sense, and pace into a specific little activity. The interface then gets out of the way. In a reproducible test on my Mac, the balcony / sounds / seated / five-minute selection returned a three-cue card from local Ollama. The code also checks for a valid card and rejects an incomplete response. I wanted an outdoor prompt that does not require giving a service my location or keeping a network connection open. Once I download the model, inference runs on my Mac, even without internet. I can inspect and change the prompt, swap the model in one environment variable, and run the app without a per-request fee. That makes this a small experiment that someone else can adapt for their own setting and language. The tradeoff is clear too: a 1B model sometimes writes repetitive or awkward cues. The app validates structure, but it cannot verify that every suggestion fits a real place. People should use their judgment and stay in safe, accessible areas. I did not record or publish a DevRelay agent session, so there is no session link to embed. The build notes show the implementation and verification steps. Best Use of Gemma. The app runs Google's open-weight gemma3:1b locally through Ollama. Every field card depends on Gemma's generated cues and reflection question. I am not entering any other partner category because this project does not use those partners' technologies.