{"slug": "touchgrass-ai-local-gemma-2b-micro-adventure-generator", "title": "TouchGrass AI: Local Gemma 2B Micro-Adventure Generator", "summary": "A developer built TouchGrass AI, an offline-first web app that uses a locally run Gemma 2B model to generate hyper-local, three-step real-world observation quests based on the user's environment and available time. The core engineering challenge was constraining the 2B model to output realistic physical tasks rather than fictional narratives, solved by enforcing a rigid JSON schema in a C# backend and restricting the prompt from inventing fictional characters.", "body_md": "*This is a submission for the [Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass](https://dev.to/challenges/hacktoberfest-week1-2026-10-05)*\n\n**TouchGrass AI** is a lightweight, offline-first web application that generates hyper-local, 3-step micro-adventures. The goal is simple: make the screen the shortest part of the experience. \n\nYou select your current environment (e.g., a local park, city center, or quiet neighborhood) and the time you have available. The app instantly generates a unique real-world observation quest. Instead of scrolling, you get specific physical tasks-like finding a distinct architectural feature, observing specific colors in nature, or completing a walking challenge. You lock your device, put it in your pocket, and actually interact with the physical world around you.\n\n`gemma2:2b` running locally via The core challenge was taming a lightweight 2B model to generate realistic, physical tasks instead of fictional role-playing narratives (initially, it tried to send me on a detective quest to investigate a fictional neighbor). By enforcing a rigid JSON schema in the C# backend and explicitly restricting the prompt from inventing fictional characters, the API reliably outputs highly contextual, real-world tasks formatted as clean JSON arrays.\n\nBuilding this with an open-source model was mandatory for the core concept to work:", "url": "https://wpnews.pro/news/touchgrass-ai-local-gemma-2b-micro-adventure-generator", "canonical_source": "https://dev.to/shadow16ua/touchgrass-ai-local-gemma-2b-micro-adventure-generator-4kbp", "published_at": "2026-10-10 08:02:15+00:00", "updated_at": "2026-10-10 08:10:52.075701+00:00", "lang": "en", "topics": ["ai-tools", "large-language-models", "generative-ai", "ai-products"], "entities": ["TouchGrass AI", "Gemma 2B", "Hacktoberfest", "C#"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/touchgrass-ai-local-gemma-2b-micro-adventure-generator", "markdown": "https://wpnews.pro/news/touchgrass-ai-local-gemma-2b-micro-adventure-generator.md", "text": "https://wpnews.pro/news/touchgrass-ai-local-gemma-2b-micro-adventure-generator.txt", "jsonld": "https://wpnews.pro/news/touchgrass-ai-local-gemma-2b-micro-adventure-generator.jsonld"}}