Multi-Agent

• A multi-machine agent stack — Run coding and research agents across several machines at once — in parallel, able to coordinate, mixing local and frontier models — and stay in control of what they do.
• Connect machines with hcom — Put a private network under your machines, run one MQTT broker, join each machine to an encrypted agent bus, and drive every machine's amux from one hub.
• hcom — A cross-machine, end-to-end-encrypted message bus that lets agents on different machines coordinate — claim tasks, flag collisions, pass results.
• Multi-agent orchestration — Run several scoped agents instead of one that does everything — for parallelism and for focused context — and coordinate them with a manager, a pipeline, or a shared bus.

← All tags