Urgent.News

What's breaking now, across thousands of outlets.

AI

I built an outdoor game that uses AI to get you off your phone

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass What if an app's most important feature was knowing when to get out of your way? Most apps compete for your attention. They want you to open them more often, spend more time inside them, and come back tomorrow. For this challenge, I wanted to build something with the opposite goal. I built GrassQuest , an…

Here is my account of the story in my own words:

GrassQuest is an outdoor exploration game that uses artificial intelligence to turn the player's real surroundings into quests. Rather than competing for the player's attention, the app aims to get people to put their phones away and spend time exploring the outdoors.

The game uses local weather data, sunrise/sunset times, and information about nearby outdoor features to generate quests that are relevant to the player's current environment. For example, if a pond is present nearby, a quest requiring a pond will appear. Severe weather will trigger easier quests to protect the player's progress.

GrassQuest presents three quest options - an "Easy Win," a "Sweet Spot" with a 65% completion probability, or a "Stretch" quest that's more challenging. The difficulty is estimated based on factors like weather, time of day, effort required, distance to features, and the player's past performance.

Once a quest is accepted, an audio briefing from the game's narrator, The Ranger, is delivered. The Ranger provides context appropriate to the weather and quest, then the player puts their phone away and begins the adventure. When they return, they submit a photo as proof.

GrassQuest verifies the photo locally using the open-source Gemma 4 Vision model running on the player's computer through Ollama. It can confirm a successful attempt, award partial points for a near miss, or give feedback for an unsuccessful attempt. Identifiable elements in the photo like plants, trees, animals, insects and weather conditions are also identified.

Completing a quest awards experience points that level up the player, "seeds" that can be spent on game upgrades, and a record of discoveries that grows the player's Field Guide over time. Badges and leaderboards add competition. The game is built open-source so anyone can run their own instance to keep personal data private.

GrassQuest was built for the DEV Hacktoberfest Open-Source AI Challenge and aims to give people a reason to get outside and explore the world around them, rather than just pass time on their phones.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in AI

Cortex AI: Adaptive Outdoor Puzzles Powered by Open-Source AI on Render

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass What I Built Cortex AI Puzzles is an adaptive, interactive puzzle platform designed to challenge cognitive…

  • Cortex AI offers adaptive outdoor puzzles to enhance cognitive thinking
  • Puzzles include Quantum Sudoku, Neural Crossword, Matrix Word Search, and Generative Jigsaw
  • Platform hosted on Render for fast response and independence

NatureQuest — Anti-Retention Outdoor Companion Powered by Local Qwen2.5

This is an official submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass . What I Built NatureQuest is a local-first outdoor adventure companion that turns a few free minutes…

  • NatureQuest promotes anti-retention through outdoor adventures.
  • Powered by local Qwen2.5 model for personalized micro-adventures.
  • Users input time and surroundings to generate safety-conscious tasks.

More from Sunday 11 October →