I Gave a Local AI One Job: Get Me Off the Screen 🌿

Description and use

GrassQuest Local uses a local Gemma 3 4B model to generate short outdoor tasks, replacing endless screen scrolling with real walks, saving progress in the browser, and operating offline after mission creation.

Problem

Developers, students, and desk‑bound workers spend excessive time scrolling on screens instead of taking real‑world breaks.

Outcome

GrassQuest Local enables users to replace screen scrolling with real‑world outdoor missions, reducing screen time and promoting physical activity while remaining fully offline after mission generation.

Workflow

• Choose break duration, environment, goal, and companions
• Generate a quest via local Gemma 3 4B
• Enter Pocket Mode, use timer, and check off tasks
• Finish adventure and track progress in browser storage
• Refresh page and restore saved progress

Evidence

GrassQuest Local is built as a local-first application rather than a cloud-AI wrapper.

Source

To run it locally, install the .NET 10 SDK and Ollama, pull the model, and start the application: ollama pull gemma3:4b dotnet restore dotnet run

Source

The app also saves your mission and progress in the browser, so refreshing the page doesn't mean losing your adventure.

Source