thepragmaticquant.com

waitbus

A workstation-local event bus: your AI coding agents wait on events instead of polling — and hear each other fail.

A narrated 50-second tour: why polling burns tokens, the event flavors waitbus speaks, and a swarm waking from a single broadcast.
Transcript

Your Claude Code and your Cursor can't hear each other — even side by side on the same machine. So they wait the wasteful way: polling, eighty times, learning nothing. waitbus replaces all of it with one call that sleeps until the event lands.

Whatever you're waiting on — GitHub, your tests, Docker, a file, or your own plugin, which waitbus makes easy to write, for Slack, Jenkins, anything — waitbus collapses them all into a single wait.

And because every tool on the box shares one local bus, when one agent fails, every other tool hears it the instant it happens — even across vendors. Each one runs its own handler. waitbus just delivers the event.

A local nervous system for your coding agents. Try it in one command: uvx waitbus demo.