🌿 NatureQuest AI: Turn Screen Time into Green Time with Open-Source AI

What if AI didn't ask you to spend more time on your screen—but inspired you to step outside?

NatureQuest AI is an AI-powered outdoor adventure application that transforms everyday nature exploration into fun, interactive missions. It encourages users to put their devices down, explore the world around them, observe nature, and build healthier digital habits.

This is my submission for the Hacktoberfest Open-Source AI Challenge — Week 1: Touch Grass.

We use technology for almost everything—learning, communication, entertainment, and work. But sometimes, scrolling through a screen replaces the simple experiences that make life interesting.

We might spend hours indoors without noticing the birds outside, the plants around us, or the small details of our environment.

I wanted to explore a different question:

Can we use AI to encourage people to spend more time in the real world instead of keeping them glued to a screen?

That question inspired me to build NatureQuest AI.

NatureQuest AI turns outdoor exploration into a mission-based experience.

Instead of simply opening another app to scroll, users can discover a challenge, go outdoors, complete the activity, and track their progress.

Feature note: Keep the photo and bird-audio features described as available only if their verification flow has been implemented and tested. Otherwise, label them as work in progress.

flowchart TD A["🌿 Open NatureQuest AI"] --> B["Choose or Generate a Mission"] B --> C["🤖 AI Suggests an Outdoor Challenge"] C --> D["🌳 Go Outside and Explore"] D --> E{"Does the Mission Require Evidence?"} E -- "Yes" --> F["📸 Photo or 🐦 Audio Evidence"] F --> G["🔍 Verify Evidence"] G --> H{"Evidence Accepted?"} H -- "No" --> I["Try Again"] I --> F H -- "Yes" --> J["Complete Mission"] E -- "No" --> J J --> K["🏆 Earn XP and Update Progress"] K --> L["📔 Record the Experience"] L --> M["Explore the Next Mission"] The important idea is that AI creates the opportunity, but the real experience happens outside the application.

Evidence verification should be used only for relevant missions. Activities that do not require evidence should continue through the normal completion flow.

NatureQuest AI is designed around an open-weight AI workflow for mission generation, with a separate application layer for mission management and progress tracking.

flowchart TB U["👤 User"] --> FE["Next.js + TypeScript Frontend"] FE --> API["FastAPI Backend"] API --> MS["Mission Service"] MS --> AI["Open-Weight AI Model"] AI --> MS MS --> VAL["Validate Mission Structure"] VAL --> FE FE --> OUT["Outdoor Activity"] OUT --> EV["Optional Evidence Submission"] EV --> VER["Evidence Verification"] VER --> COMPLETE["Mission Completion Logic"] COMPLETE --> XP["XP, Streaks and Badges"] XP --> JOURNAL["Nature Journal and Progress"] What each layer does Component Responsibility Frontend Displays missions, progress, and the user interface Backend API Handles requests and application logic Mission service Organizes mission generation and mission data Open-weight model Generates outdoor mission ideas Evidence verification Evaluates relevant photo or audio submissions Progress system Tracks completion, XP, streaks, and badges Nature Journal Records the user's outdoor experiences The exact inference provider and verification models depend on the implementation used in the final application.

Important: Keep only the technologies and AI models actually used in your project. If you use a different model or inference setup, update this table accordingly.

Open innovation is important because developers should have choices in how they build and deploy AI-powered applications.

For NatureQuest AI, open-weight models create opportunities to experiment with mission generation, test different models, and explore local inference where the model and hardware support it.

Open-weight models do not automatically make an application free, completely private, or fully offline. Those properties depend on the model licence, deployment, hardware, data handling, and external services.

For me, the most interesting part is using open AI for something beyond another chatbot: encouraging people to reconnect with nature.

Imagine a user opens NatureQuest AI on a Saturday morning.

The activity is simple, but it encourages observation, curiosity, and time away from endless scrolling.

Evidence verification can help discourage unsupported completion claims, although an AI classifier cannot guarantee that every submission is genuine or correctly identified.

I wanted the interface to feel calm, natural, friendly, and inviting—not like a corporate dashboard.

The design supports the purpose of the application: make outdoor exploration feel accessible and enjoyable.

Building NatureQuest AI helped me think about AI as part of a complete product, rather than just a model that generates text.

Some important engineering considerations include:

One lesson stands out: AI features are only useful when they support a meaningful user experience and work reliably within the limits of the system.

Before publishing, add one or two challenges you personally encountered and solved during development. Real examples make this section stronger.

NatureQuest AI can grow in several directions:

These are potential improvements, not claims that all of them are already implemented.

Replace these placeholders with real, publicly accessible image URLs. You can also embed a short demo video.

Try NatureQuest AI: https://drive.google.com/file/d/1E4YNQP3uqlSZSev_cjVn-vvIMQ2dOOsF/view?usp=sharing

If the application is not deployed yet, replace this section with a short video demonstration or remove it until the demo is available.

GitHub Repository: https://github.com/Rishabh-KSingh/NatureQuest-AI

The repository contains the project source code and implementation details.

If you are interested in open-source AI, nature-based applications, or creative uses of technology, feel free to explore the project and share feedback.

Please follow the contribution instructions in the repository before submitting changes.

Use the repository's actual installation instructions if they differ from this example.

# Clone the repository git clone YOUR_GITHUB_REPOSITORY_URL # Enter the project directory cd YOUR_PROJECT_DIRECTORY Enter fullscreen mode Exit fullscreen mode Install frontend and backend dependencies using the instructions and dependency files included in the repository.

Configure the required environment variables, then start the frontend and backend using the project's documented development commands.

Note: The commands above are a starting point, not a complete verified setup guide. Add the exact install, environment configuration, and run commands from your working repository before publishing.

NatureQuest AI began with a simple idea:

What if we built AI that encouraged people to spend less time looking at screens and more time looking at the world?

I wanted to explore a positive use of technology—one that inspires curiosity, supports outdoor activities, and makes reconnecting with nature more engaging.

This project is my contribution to the Touch Grass challenge, and I hope it inspires other developers to experiment with open-source AI in creative, human-centered ways.

Technology doesn't always have to keep us online. Sometimes, it can give us a reason to step outside.

🌿 Build with AI. Explore with curiosity. Reconnect with nature.

I'd love to hear your feedback and ideas!

Expand DEV SUPPORTS DEV SUPPORTS DEV SUPPORTS Follow Joined Oct 9, 2026 • Oct 12 Dropdown menu Copy link Hide You need to verify your account. Enter fullscreen mode Exit fullscreen mode tr.ee/dev-to