Loading page...Загружаем страницу...正在加载页面...
AtlasRepo

TouchGrass AI: An Open-Source AI Outdoor Mission Planner

Description and use

TouchGrass AI is an open-source outdoor mission planner that lets users select time, activity, difficulty, and mode, receive a concise mission, put their phone away, complete it outdoors, and then return to mark completion. It uses React, FastAPI, SQLite, and an open-weight Gemma model with a deterministic fallback, deployed on Render.

Problem

Digital products often keep users on the screen, but TouchGrass AI aims to reduce screen time by providing brief AI-generated outdoor missions.

Outcome

The application successfully generates short outdoor missions, encourages users to reduce screen time, and records mission completion with statistics, demonstrating that AI can facilitate brief interactions rather than prolonged engagement.

Workflow

  • Select available time (15, 30, or 60 minutes)
  • Choose activity (Walking, Nature, Photography, Exercise, Social)
  • Choose difficulty (Easy, Medium, Hard)
  • Choose mode (Solo or With Friends)
  • Backend generates structured mission
  • App provides actionable checklist
  • User goes outside and completes mission
  • User returns to mark completion, mission saved to history and statistics updated

Evidence

TouchGrass AI creates short, practical outdoor missions based on: Available time: 15, 30, or 60 minutes, Activity: Walking, Nature, Photography, Exercise, or Social, Difficulty: Easy, Medium, or Hard, Mode: Solo or With Friends

Source

The app gives the user an actionable outdoor objective and encourages them to put their phone away once the mission starts.

Source

The deployed application is using the tested deterministic fallback path.

Source

I actually used the deployed application for an outdoor mission. I generated a mission, started it, put the phone away, went outside, completed the activity, and then returned to mark the mission complete.

Source

  • Record date: 2026-10-07T21:55:55.406Z