The latest articles on DEV Community by Aarav yadav (@aarav_yadav_5a746f06d08a0). https://dev.to/aarav_yadav_5a746f06d08a0 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%2F4173009%2F3dc1720f-05c6-4ed8-be60-7f7b6c32f6ec.png https://dev.to/aarav_yadav_5a746f06d08a0 en Aarav yadav Fri, 09 Oct 2026 11:20:49 +0000 https://dev.to/aarav_yadav_5a746f06d08a0/greenquest-ai-turning-open-source-ai-into-real-world-adventures-hacktoberfest-touchgrass-3e7c https://dev.to/aarav_yadav_5a746f06d08a0/greenquest-ai-turning-open-source-ai-into-real-world-adventures-hacktoberfest-touchgrass-3e7c <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> <h2> What I Built </h2> <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%2Fkrga28o7sxkkhatg9fob.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%2Fkrga28o7sxkkhatg9fob.png" alt=" " width="800" height="533"></a></p> <p>I built <strong>GreenQuest AI 🌿</strong>, an AI-powered outdoor activity companion that encourages people to spend less time scrolling on their phones and more time exploring nature.</p> <p>Users can select their mood, available time, and interests to generate personalized outdoor quests. Activities include exploring plants and trees, observing birds, walking outdoors, and gardening.</p> <h3> Key Features </h3> <ul> <li>🤖 AI-powered nature quest generation</li> <li>🌳 Personalized outdoor activities</li> <li>🏆 Points for completing quests</li> <li>💾 Progress saved using browser local storage</li> <li>📱 Responsive design for different screen sizes</li> <li>🌱 Built-in fallback activities if AI generation fails</li> </ul> <p>The goal is to use technology to encourage real-world experiences rather than endless screen time.</p> <h2> Demo </h2> <p>🌐 <strong>Live Website:</strong> <a href="https://aaravyadav192007-crypto.github.io/GreenQuest-AI/" rel="noopener noreferrer">https://aaravyadav192007-crypto.github.io/GreenQuest-AI/</a></p> <p>Try GreenQuest AI and generate your own nature quest!</p> <h2> Code </h2> <p>💻 <strong>GitHub Repository:</strong> <a href="https://github.com/aaravyadav192007-crypto/GreenQuest-AI" rel="noopener noreferrer">https://github.com/aaravyadav192007-crypto/GreenQuest-AI</a></p> <p>The project source code is available on GitHub.</p> <h2> How I Built It </h2> <p>I built GreenQuest AI using HTML, CSS, and JavaScript, with Hugging Face Transformers.js for browser-based AI inference.</p> <p><strong>Technologies used:</strong></p> <ul> <li>HTML5 for the website structure</li> <li>CSS3 for styling, animations, and responsive design</li> <li>JavaScript for interactivity and application logic</li> <li>Hugging Face Transformers.js for running AI models in the browser</li> <li>Qwen2.5-0.5B-Instruct as the intended open-weight language model for generating nature quests</li> </ul> <p>The user selects their mood, available time, and interests. JavaScript creates a prompt, the AI generates a nature quest, and the website displays the result. Users can then complete the quest and earn points.</p> <p>The application is designed to run AI inference in the browser without requiring a paid AI API key. An internet connection is needed to download the model initially unless the required files have already been cached or hosted locally.</p> <h2> Why Does Open Innovation Matter? </h2> <p>Open innovation makes it easier for students and developers to experiment with AI, customize applications, and learn without depending entirely on proprietary services.</p> <p>For GreenQuest AI, an open-weight model offers several advantages:</p> <ul> <li> <strong>Flexibility:</strong> Developers can experiment with compatible models and customize prompts.</li> <li> <strong>Cost efficiency:</strong> No paid AI API is required for each quest-generation request.</li> <li> <strong>Privacy:</strong> User preferences can be processed locally in the browser.</li> <li> <strong>Local inference:</strong> The model can generate activities on the user's device after its files are available.</li> <li> <strong>Learning:</strong> The project demonstrates how open-weight AI can be integrated into a practical web application.</li> </ul> <p>I believe AI should not only keep people engaged with screens. It can also encourage them to disconnect, explore their surroundings, and reconnect with nature.</p> <h2> My Agent Session </h2> <p>No agent-session recording is included yet. I may add a DevRelay session link after recording one.</p> <h2> Prize Categories </h2> <ul> <li>Touch Grass — Week 1</li> </ul> <h2> What's Next? </h2> <ul> <li>🌿 Plant identification using images</li> <li>🐦 Bird identification and nature challenges</li> <li>🗺️ Outdoor activity recommendations based on location</li> <li>🏅 Daily challenges, achievements, and badges</li> <li>📶 Improved offline functionality</li> </ul> <p>This project helped me explore how open-weight AI can be combined with frontend development to create something useful beyond the screen.</p> <p><strong>Built by Aarav Yadav 🌿</strong></p> <p>🔗 <a href="https://aaravyadav192007-crypto.github.io/GreenQuest-AI/" rel="noopener noreferrer">Live Demo</a> | <a href="https://github.com/aaravyadav192007-crypto/GreenQuest-AI" rel="noopener noreferrer">GitHub Repository</a></p> <h1> Hacktoberfest #OpenSource #AI #JavaScript #TouchGrass </h1> devchallenge hf26challenge