{"slug": "touchgrass-ai-stop-scrolling-start-exploring", "title": "🌱 TouchGrass AI: Stop Scrolling, Start Exploring", "summary": "A developer built TouchGrass AI, a local Streamlit and Ollama application that uses the open-weight Llama 3.2 3B model to generate short, practical outdoor missions from a user's available time, preferred activity, and company. The project, submitted to the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass, sends prompts to Ollama's local API at localhost:11434 and displays the resulting 3–5 step challenge, with source code available on GitHub. Its stated goal is to make the screen the shortest part of the experience rather than another app that keeps users chatting with AI.", "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\nI built **TouchGrass AI**, a local AI-powered outdoor activity companion designed to help people spend less time on screens and more time in the real world.\n\nThe idea is simple:\n\n**Use AI for a few seconds → get an outdoor mission → put the phone away → go outside. 🌱**\n\nThe user chooses:\n\nTouchGrass AI then uses a locally running AI model to generate a short, practical outdoor mission.\n\nFor example, a user with 30 minutes who chooses Nature can receive a simple nature exploration challenge with 3–5 steps.\n\nThe project is designed for anyone who wants a quick reason to walk, explore, observe nature, or spend time outdoors with friends and family.\n\nThe goal isn't to create another app that keeps users chatting with AI.\n\n**The goal is to make the screen the shortest part of the experience.**\n\nThe project currently runs locally using Streamlit and Ollama.\n\nI will include a short screen recording showing:\n\nThe complete source code is available on GitHub:\n\n[https://github.com/Samruddhipathrikar/TouchGrassAI](https://github.com/Samruddhipathrikar/TouchGrassAI)\n\nThe repository contains the Streamlit application and its dependencies.\n\nI built TouchGrass AI using Python, Streamlit, Ollama, and the open-weight **Llama 3.2 3B** model.\n\nThe user interacts with a simple Streamlit interface.\n\nThe application collects the user's:\n\nThese inputs are converted into a prompt for the local Llama 3.2 model.\n\nThe application sends the prompt to Ollama through its local API:\n\n`http://localhost:11434/api/chat`\n\nThe generated response is then displayed as the user's outdoor mission.\n\n```\ntext\nUser\n  ↓\nStreamlit UI\n  ↓\nTime + Activity + Company\n  ↓\nPrompt\n  ↓\nOllama Local API\n  ↓\nLlama 3.2 3B\n  ↓\nOutdoor Mission\n  ↓\n🌱 Go Outside\n```\n\n", "url": "https://wpnews.pro/news/touchgrass-ai-stop-scrolling-start-exploring", "canonical_source": "https://dev.to/samruddhipathrikar/touchgrass-ai-stop-scrolling-start-exploring-4375", "published_at": "2026-10-08 16:10:11+00:00", "updated_at": "2026-10-08 16:20:08.724352+00:00", "lang": "en", "topics": ["ai-tools", "large-language-models", "ai-products"], "entities": ["TouchGrass AI", "Ollama", "Streamlit", "Llama 3.2 3B", "GitHub", "Hacktoberfest Open-Source AI Challenge", "Samruddhipathrikar"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/touchgrass-ai-stop-scrolling-start-exploring", "markdown": "https://wpnews.pro/news/touchgrass-ai-stop-scrolling-start-exploring.md", "text": "https://wpnews.pro/news/touchgrass-ai-stop-scrolling-start-exploring.txt", "jsonld": "https://wpnews.pro/news/touchgrass-ai-stop-scrolling-start-exploring.jsonld"}}