Skip to Main Content

Cortex is a memory for your computer that remembers what you use, lets unused detail fade, and helps an AI assistant keep up with your life. It turns screenshots and interactions into structured memories linked to their original evidence. Explore them in a 3D memory palace, inspect their connections in a memory graph, and talk to Cortex through a voice-enabled desktop companion. Frequently used memories stay useful, while neglected screenshot detail progressively loses resolution. Our demo follows Maya across everyday tasks—from finding an apartment to returning an IKEA purchase. Cortex brings together context scattered across her browsing, emails, and calendar so she doesn’t have to explain everything again. When her circumstances change, like deciding to get a dog, that new information can reshape what matters for her apartment search. Instead of keeping an ever-growing archive of everything, Cortex explores how AI can retain useful context, let go of unnecessary detail, and help with the next task.

Team

Arshnoor-kauravneetsingh36

Placement

Participant

More from The Harness Engineering & Model Wrangling Hackathon

Ripple designs circuit boards from plain English, grades them against hidden checks, and evolves its own harness from the failures, going from 0/4 to 3/4 on…

Ripple project preview

Offload learns the work you repeat, so next time you can hand it over. Its engine, REM (Replay · Evolve · Merge), is an agent harness with a day/night cycle…

Offload project preview

Recursive Computer Use is a local-first desktop automation harness that enables AI agents to execute tasks on your computer, verify outcomes locally, and…

Morgadarsha project preview

Da Vinci is a recursive improvement CAD harness designed to support physical engineering tasks through specialized AI agents, programmatic CAD and automated…

Da Vinci: Recursive Improvement CAD Harness project preview

CyclopsDiary gives factory workers wearing Meta AI glasses a shared memory of the floor. Every worker's glasses feed one MongoDB memory that keeps what was…

CyclopsDiary project preview

A harness that teaches itself what context to show Jev, TypeSafe's fast decision model, proves the result on a storm it never saw, and can't cheat because…

www.loom.com/…