Interesting, what is the timeline for the wrapped feature? Is it yearly? Or is the window shorter?

Currently the wrapped feature supports two windows, past 24 hours and last 7 days.

interesting idea. the “local swarm of small agents” approach feels like a natural direction compared to sending everything to a single large model in the cloud. i’m curious how coordination between the agents works in practice. is there some central planner deciding which agent handles what, or do they communicate more peer-to-peer?

also wondering how well this scales when the number of agents grows — does orchestration become the main challenge at that point?

Currently it supports up to 8 agents at a time. The sub-agent hook is only supported by Claude and Cursor for now. As more platforms begin supporting hooks, we can extend this toward agent-to-agent orchestration, where agents can delegate tasks to other agents.