How Klåd stays responsive while working, scales to multiple users, and keeps every tenant completely isolated.
When Klåd is building or deploying, the group queue blocks. New messages wait up to 15 minutes. You can't get a status update or change direction mid-task.
A long-lived Coordinator per group handles all messages instantly, classifies them, and spawns parallel Worker containers for heavy tasks. Workers run in isolation. Only the Coordinator writes to memory.
Each user gets their own fully isolated Klåd instance — separate bot, database, and memory. Neither instance knows the other exists.
Every boundary is enforced at the container level — not just by convention.
Full scripts are in the repo. Here's the outline: