I run four or five Claude Code sessions concurrently on the same repo and got tired of juggling worktrees. crew hooks into Claude Code and injects what every other running session is doing (status, recap, last few transcript entries) into each session's context. They can also message each other: crew send lands in another agent's context within seconds, even mid-turn.
Since starting to use crew I've seen some awesome emergent behaviors: agents asking each other for reviews, delegating deploys to a single agent, and even getting lazy on account of "someone else will fix it"!
Curious how others running several sessions at once handle coordination.
Comments URL: [https://news.ycombinator.com/item?id=48782800](https://news.ycombinator.com/item?id=48782800)
Points: 1
source & further reading
github.com — original article