# Zomma

- **Event:** [Zero to Agent: Vercel x Deepmind Hackathon NYC](https://cerebralvalley.ai/e/zero-to-agent-nyc)
- **When:** Sat, Mar 21 at 9:00 AM – 10:00 PM (EDT)
- **Where:** 220 W 26th St, New York, NY
- **Team:** [Jihyun Kim](https://cerebralvalley.ai/u/jihyun), [Cashel Fitzgerald](https://cerebralvalley.ai/u/cash)
- **GitHub:** https://github.com/zomma-dev/aria-app
- **Demo video:** https://youtu.be/Jj6wgusny9Y
- **Gallery:** https://cerebralvalley.ai/e/zero-to-agent-nyc/hackathon/gallery
- **Page:** https://cerebralvalley.ai/e/zero-to-agent-nyc/hackathon/gallery/56

Aria is a desktop AI agent that learns how work gets done. Instead of treating every task as a brand-new problem, Aria recognizes recurring workflows, grounds them into structured action graphs, and uses that memory to execute familiar tasks faster and more reliably over time.

We have three layers: perception, reasoning, and graph retrieval.

- Perception: A vision-language model interprets screenshots to extract the current UI state, visible affordances, and action-relevant context from the desktop.
- Reasoning: A reasoning model uses this state to plan the next step, decide when to explore, and recover from ambiguity in the environment.
- Graph Retrieval: In parallel, a knowledge-graph agent queries previously stored workflow graphs to find similar task trajectories, matching on intent, interface state, and prior action structure.

When a match workflow exists, Aria can follow or adapt an existing graph instead of replanning from scratch. When no match is found, it falls back to live reasoning and converts the new successful run into graph memory for future reuse.

---

Markdown version of https://cerebralvalley.ai/e/zero-to-agent-nyc/hackathon/gallery/56. Site index for agents: https://cerebralvalley.ai/llms.txt · full text: https://cerebralvalley.ai/llms-full.txt