Skip to Main Content

Every recommender has the same blind spot: tell it to forget something, and it quietly learns it right back. We built the fix, a governed memory layer on MongoDB Atlas that makes forgetting actually stick, by retracting the evidence behind a memory instead of just its label, and repairing only the decisions that depended on it. The results speak for themselves: naive forgetting brings the forgotten content back at rank 1 in every session, ours keeps it gone in all three, and the same core powers a completely different domain without changing a single line of code.

Team

its_tomiMicgr8taniketqxp+1

More from Agents in Context Toronto: a MongoDB Hackathon

We simulate real world agent to agent systems built on MongoDB, Langchain (harnesses) ready for use in production to defend all systems. A swarm of real AI…

Legacy Siege project preview

suture is an incident-recovery agent that finishes the job even when its worker crashes mid-run. Cleaning up a leaked key takes a chain of writes across…

suture project preview

Venues play one playlist for everyone, and the apps that let guests shape the music keep their likes on view with no easy way to take them back. Musory: your…

Musory project preview

Robots are starting to learn from people, and fleets can share what one robot learns with every other robot. Nobody can yet answer three questions: who taught…

One Lesson project preview

Phylax Tower is a safety net for airport control towers. In March 2026 at LaGuardia, a jet was cleared to land, and two minutes later a fire truck was cleared…

Phylax Tower project preview

New hires hit the ground at light speed. New devs lose their first days juggling broken setup guides, each solving the same problems alone. Day One finishes…

Day One project preview