TouchGrass AI: An Open-Source AI Companion to Help You Touch Grass

Description and use

TouchGrass AI is an open‑source app that uses AI to generate small outdoor quests, encouraging users to step away from screens and improve digital well‑being.

Problem

People spend excessive time on screens and lack motivation to step outside and engage in real‑world activities.

Outcome

The app successfully provides actionable outdoor quests, tracks user engagement, and remains functional even without AI, demonstrating a viable open‑source solution for digital well‑being.

Workflow

• 1. User opens the app and logs in.
• 2. App displays daily quests or generates new ones via the Qwen 2.5‑3B model on Ollama.
• 3. User completes a quest and marks it as done.
• 4. App awards XP, updates streaks, and records the activity in field notes.
• 5. User reviews progress and sets custom quests if desired.

Evidence

we spend so much time looking at screens that sometimes we forget to experience the world outside them.

Source

touchgrass ai is an open-source, ai-powered wellness app that encourages people to step away from their screens and reconnect with the real world through small, achievable activities.

Source

instead of just telling you to spend less time online, it gives you little outdoor quests to complete in real life.

Source

i used the following technologies: frontend: react, vite, and css; backend: python and fastapi; open-source ai: qwen 2.5 3b through ollama; storage: browser local storage; deployment: vercel for the frontend and render for the backend.

Source

using an open-weight model such as qwen 2.5 3b through ollama gives developers the freedom to experiment with local inference, customize model behavior, and explore different models without depending on a paid proprietary ai api.

Source