I Built an AI Gardening App That Tells Me to Put the Laptop Down

Description and use

Garden Trials lets gardeners systematically observe, experiment, and record evidence using a local Gemma 1B model via Ollama, without cloud dependence.

Problem

Gardeners often lack a simple tool to guide observation, experiment, and evidence tracking while keeping the focus on hands‑on care.

Outcome

Garden Trials enables gardeners to perform controlled, repeatable observations and experiments locally without cloud dependencies, producing evidence tables and actionable next steps while keeping the gardener’s hands in the soil.

Workflow

• Write a note about a plant and the day you saw it.
• The local Gemma model reads the note into plain facts.
• The app asks you to check one specific thing on the plant.
• You record the observation and optionally pick one change from a small menu.
• You count and take a photo, matching the angle with the last photo shown.
• The app shows a table, chart, verdict, evidence level (0‑3), and a plain next step.

Evidence

Garden Trials is a small app that runs entirely on your own computer.

Source

The stack is small on purpose: Streamlit, one JSON file, and gemma3:1b running locally through Ollama.

Source

Setup is in the README: Python 3.11 or newer, Ollama, ollama pull gemma3:1b, then python -m streamlit run app.py.

Source