Inspiration
As AI use grows, its environmental impact remains invisible. We wanted to make the hidden costs of AI—water, energy, and carbon—visible so users can understand and take responsibility for their usage.
What it does
Varuna tracks AI token usage and converts it into real-world environmental metrics like water consumption, electricity usage, and CO₂ emissions in real time.
How we built it
We used the Gemini API to measure token usage, applied conversion formulas to estimate environmental impact, and built a web app with a backend API, database storage, and a live dashboard.
Challenges we ran into
The biggest challenge was translating abstract token counts into meaningful, defensible environmental metrics while keeping the system simple and understandable.
Accomplishments that we’re proud of
We built a working end-to-end system that makes AI’s environmental impact tangible and easy to compare, rather than abstract and hidden.
What we learned
We learned how to work together and create a sustainable github repository to work with. We learned the hard way that we couldn't go at it without a plan.
What’s next for Varuna
Next, we want to add persistent user tracking, organizational dashboards, and deeper integrations so sustainability becomes part of everyday AI workflows.
Log in or sign up for Devpost to join the conversation.