DEV Community

Side Hustle OS

Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle Submission 💸

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle

What I Built

I built Side Hustle OS, an AI-powered outdoor companion designed to help people spend less time scrolling and more time exploring the real world. It encourages users to discover nature, learn about plants and birds, explore trails, and engage in activities such as gardening and outdoor exploration.

Demo

Code

GitHub logo aishik-1 / Side-Hustle

Platform for working professionals and Students

How I Built It

Idea and planning: I started with the idea of using AI to help people reconnect with nature through activities such as exploring trails, learning about plants and birds, and gardening.

AI-assisted development: I used AI coding assistants to help plan the project, develop and refine the code, design the user interface, troubleshoot issues, and iterate on the implementation.

Product development: I focused on making the experience useful and approachable, with the goal of combining AI-powered guidance with real-world outdoor activities.

Open-source AI direction: I explored the potential of open-weight models and open-source AI tools to make BioTrail more flexible and customizable, with the possibility of local inference and reduced reliance on paid AI APIs.

Future potential: I envision expanding BioTrail with personalized outdoor challenges, nature-learning experiences, and exploration recommendations that could make it useful enough for people to pay for premium features.

The biggest takeaway was learning how to turn an idea into a working project through experimentation, AI-assisted coding, and continuous iteration. My goal is to make AI a tool that helps people experience more of the world beyond their screens.

Why Does Open Innovation Matter?

Open-source AI makes BioTrail more flexible, accessible, and adaptable. By building around open-weight models and open-source AI tools, the project can evolve without depending entirely on a single closed AI provider. Models can be swapped, customized, or eventually run locally, depending on the available hardware and implementation.

Top comments (0)