Team 28

Atmos

Personal Agentic AI for your Day

Check your own project

Community votes recognize the build and do not affect official judging.

Review the project

Start with the source code, then open the demo or video if available.

View GitHub repository
Project description
Atmos is a agentic AI that exists and communicates with the Atmos environment. It remembers what matters to you and keeps track of what’s happening around you. A traveler can say, “I’m visiting San Francisco for a hackathon, I want vegan food, and I’d like to see friends,” and get a day they can explore and adjust on a map. The platform envisioned has two kinds of memory stored within Cognee: Shared city memory. Always-running agents would follow event pages, organizer and attendee posts, and restaurant updates to track schedules, openings, closures, ratings, menus, prices, and expected waits. Private traveler memory. Atmos remembers dietary restrictions, daily habits, budget, walking goals, calendar commitments, and who the traveler wants to see. Those details shape which options it recommends. The AI agent has been rigorously tested within Firedrill's simulation environment to predict and plan for any user's interests and accommodations needed to improve their daily lives.
Tools used