This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass
What I Built
Demo
Code
How I Built It
Why Does Open Innovation Matter?
My Agent Session
Prize Categories
building something that is genuinely useful outdoors but simple enough to finish as a beginner.
The key is that this isn't just a normal website with an AI chatbot. An open-weight model or open-source AI component should actually power the project, and the screen should help people get outside faster.
My project recommendation: TouchGrass
Smartphones and artificial intelligence help detect ecological change
Add to Favorites
Audubon’s Climate Watch, Now a Decade Old, Has Tracked Shifts in Bird Ranges as Temperatures Rise | Audubon
Mutual Aid Networks: How Communities Build Their Own Safety | Science Array
Build a personal outdoor adventure generator that turns someone's free time into a real-world activity.
For example, someone opens the app, selects that they have 30 minutes, and gets a mini nature adventure near home. They might have to find three different leaf shapes, observe a bird, or identify five things in nature that they have never noticed before.
The app generates the activity using an open-weight language model, then gives the user a checklist and encourages them to put their phone away.
- What the finished project will do Wallpaper Green Leaf in Macro Photography, Background - Download Free Image
Step 1 — Choose your adventure
Select your available time: 10, 30, or 60 minutes.
Natural Resources Management Plan — Forest Park Forever
Step 2 — Get an AI-generated mission
An open-weight model creates an outdoor activity suited to your time and interests.
Aplik�cia na ur�ovanie rastl�n -
2017 - FLORA.sk ( KVETY - Z�HRADA - CHALUPA - LIFESTYLE - ZDRAVIE )
Step 3 — Explore and record
Complete the mission, optionally take a photo, and save what you discovered.
- Technology we'll use Component
Technology
Purpose
Frontend
React + Vite
Build the website
AI model
Qwen2.5 or another compatible open-weight model
Generate nature missions
Local inference
Ollama
Run the model on your computer
Storage
Browser local storage
Save completed adventures
Styling
CSS
Make the interface attractive
We'll start with AI-generated missions rather than complicated image recognition. Once the basic project works, we can add photo-based plant or nature identification.
- Your first practical step If you have a computer, we'll build and test the project locally first.
Beginner setup checklist
Install Node.js (LTS version).
Install Visual Studio Code.
Install Ollama.
Open a terminal and check that Node.js works with node -v.
Official downloads:
Node.js
Visual Studio Code
Ollama
We will then create the React app, connect it to the local model, and build the mission generator one file at a time.
- What makes this a strong open-source AI entry? Privacy: Your prompts can stay on your own computer instead of being sent to a hosted AI provider.
Offline potential: The model can generate missions without an internet connection after setup and model download. Maps and online services would still need connectivity.
Freedom to experiment: You can replace the model, customize its instructions, and modify the application.
Real-world impact: The app measures completed outdoor missions, not time spent chatting with AI.
One important distinction: Ollama is a local model runner, and the model you choose must have suitable open weights and licensing. We'll document the actual model and license in the project README.
One question before we start coding: Do you have access to a laptop or computer, or will you be building this entirely on your Android phone? That determines the easiest setup for you.
M.
Our plan is:
🌱 Build a simple website first.
🤖 Connect an open-source AI model.
🌳 Make it generate outdoor missions.
🧪 Test it and prepare your project for submission.
Top comments (0)