{
  "id": 13464856,
  "title": "I Gave a Local AI One Job: Get Me Off the Screen 🌿",
  "url": "https://urgent.news/2026/10/10/i-gave-a-local-ai-one-job-get-me-off-the-screen",
  "topic": "ai",
  "section": "AI",
  "published": "2026-10-10T16:51:16.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/dinukaek/i-gave-a-local-ai-one-job-get-me-off-the-screen-4i5h"
  },
  "original_language": "en",
  "account": "This is a submission for the Hacktoberfest Open-Source AI Challenge - Week 1: Touch Grass. The project is called GrassQuest Local, which is a local-AI-powered outdoor adventure companion. The app helps users spend less time on screens by turning short breaks into meaningful outdoor missions.\n\nTo use GrassQuest Local, users first choose the duration of their break, the outdoor environment, what they want from the break, and whether they're going solo or with someone. After setting these parameters, the app generates a personalized outdoor mission with five tasks and a 3x3 Outside Bingo board using the Gemma 3 4B model.\n\nThe user then switches to Pocket Mode to take the mission outside, using the timer to keep track of time as they complete the tasks and bingo squares. Once the adventure is finished, the app saves the mission and progress in the browser, allowing the user to easily pick up where they left off. The app is also designed to work offline, preserving the saved progress as long as the app has been cached.\n\nGrassQuest Local was built using a lightweight stack, with the AI model Gemma 3 4B serving locally through Ollama, ASP.NET Core on .NET 10 as the backend, and HTML, CSS, and vanilla JavaScript for the frontend. The app also includes a responsive interface, mission timer, task tracking, and an interactive 3x3 bingo board for the Pocket Mode experience.\n\nThe key innovation in GrassQuest Local is its use of a local AI model, which eliminates the need for a cloud AI dependency and allows for more control over the user experience. By running the AI model locally, users can generate personalized missions without relying on third-party AI APIs or obtaining separate API keys. This also makes the app more private and self-contained, as it doesn't require a cloud AI account to generate missions. The app can also continue to work offline, preserving progress as long as the app and the AI model are running locally.",
  "summary": "This is a submission for the Hacktoberfest Open-Source AI Challenge — Week 1: Touch Grass . What I Built What if the most useful AI app was one that helped you spend less time using apps? As developers, students, and people who work in front of screens all day, we know the feeling: we need a break, so we reach for our phones. Then a few minutes of scrolling becomes half an hour. I wanted to try…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}