This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass*
What I Built
I built NatureSpark, a local web application designed to counter developer burnout. Based on a user's current fatigue level and the local weather, it generates tailored, hyper-local outdoor activities (like short trail walks, park spots, or outdoor reading benches) to encourage users to step away from their monitors. It is built specifically for software engineers who struggle to disconnect from their IDEs.
How I Built It
The project relies completely on an open-source architecture:
- AI Model: Llama 3.1 (8B variant) running locally for quick inference.
- Local Inference: Powered by Ollama to handle user prompts privately without sending data to external clouds.
- Frontend: Built using Next.js and Tailwind CSS for a clean, accessible user interface.
Why Does Open Innovation Matter?
Open innovation allowed me to build this entire project locally without worrying about API keys, usage limits, or ongoing subscription costs. Using an open-weight model ensures that user privacy is strictly maintained, as all data stays on the developer's local machine while they figure out how to step outside.
Prize Categories
- Main Hacktoberfest AI Track
Top comments (0)