The latest articles on DEV Community by samruddhi (@samruddhipathrikar). https://dev.to/samruddhipathrikar https://media2.dev.to/dynamic/image/width=90,height=90,fit=cover,gravity=auto,format=auto/https:%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Fuser%2Fprofile_image%2F4155036%2Fcddc9227-495e-42a3-bbfc-06535ace140a.png https://dev.to/samruddhipathrikar en samruddhi Thu, 08 Oct 2026 16:10:11 +0000 https://dev.to/samruddhipathrikar/touchgrass-ai-stop-scrolling-start-exploring-4375 https://dev.to/samruddhipathrikar/touchgrass-ai-stop-scrolling-start-exploring-4375 <p><em>This is a submission for the <a href="https://dev.to/challenges/hacktoberfest-week1-2026-10-05">Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass</a></em></p> <h1> 🌱 TouchGrass AI — Stop Scrolling. Start Exploring. </h1> <h2> What I Built </h2> <p>I built <strong>TouchGrass AI</strong>, a local AI-powered outdoor activity companion designed to help people spend less time on screens and more time in the real world.</p> <p>The idea is simple:</p> <p><strong>Use AI for a few seconds → get an outdoor mission → put the phone away → go outside. 🌱</strong></p> <p>The user chooses:</p> <ul> <li>⏱️ How much time they have</li> <li>🌿 What outdoor activity they want</li> <li>👥 Who they are with</li> </ul> <p>TouchGrass AI then uses a locally running AI model to generate a short, practical outdoor mission.</p> <p>For example, a user with 30 minutes who chooses Nature can receive a simple nature exploration challenge with 3–5 steps.</p> <p>The project is designed for anyone who wants a quick reason to walk, explore, observe nature, or spend time outdoors with friends and family.</p> <p>The goal isn't to create another app that keeps users chatting with AI.</p> <p><strong>The goal is to make the screen the shortest part of the experience.</strong></p> <h2> Demo </h2> <p>The project currently runs locally using Streamlit and Ollama.</p> <p>I will include a short screen recording showing:</p> <ol> <li>Selecting the available time</li> <li>Selecting an outdoor activity</li> <li>Selecting who I'm with</li> <li>Generating an outdoor mission</li> <li>Taking the generated mission outside</li> </ol> <p><a href="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2Ficdry0hhp836vj6c9o6g.png" class="article-body-image-wrapper"><img src="https://media2.dev.to/dynamic/image/width=800%2Cheight=%2Cfit=scale-down%2Cgravity=auto%2Cformat=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2Ficdry0hhp836vj6c9o6g.png" alt=" " width="800" height="600"></a></p> <h2> Code </h2> <p>The complete source code is available on GitHub:</p> <p><a href="https://github.com/Samruddhipathrikar/TouchGrassAI" rel="noopener noreferrer">https://github.com/Samruddhipathrikar/TouchGrassAI</a></p> <p>The repository contains the Streamlit application and its dependencies.</p> <h2> How I Built It </h2> <p>I built TouchGrass AI using Python, Streamlit, Ollama, and the open-weight <strong>Llama 3.2 3B</strong> model.</p> <h3> Tech Stack </h3> <ul> <li>Python</li> <li>Streamlit</li> <li>Ollama</li> <li>Llama 3.2 3B</li> <li>Requests</li> </ul> <p>The user interacts with a simple Streamlit interface.</p> <p>The application collects the user's:</p> <ul> <li>Available time</li> <li>Preferred outdoor activity</li> <li>Company</li> </ul> <p>These inputs are converted into a prompt for the local Llama 3.2 model.</p> <p>The application sends the prompt to Ollama through its local API:</p> <p><code>http://localhost:11434/api/chat</code></p> <p>The generated response is then displayed as the user's outdoor mission.</p> <h3> Architecture </h3> <div class="highlight js-code-highlight"> <pre class="highlight plaintext"><code> text User ↓ Streamlit UI ↓ Time + Activity + Company ↓ Prompt ↓ Ollama Local API ↓ Llama 3.2 3B ↓ Outdoor Mission ↓ 🌱 Go Outside </code></pre> </div> devchallenge hf26challenge