Machines aren't just servers.

Why this matters

Every multi-agent platform talks about agents. Almost none talk about machines. Yet a local agent on a GPU workstation has fundamentally different capabilities than a worker on a Raspberry Pi: different memory, different latency, different model weights loaded, different power budget. Modelling that explicitly is the difference between"I have agents" and "I have a fleet".

Once a machine is a first-class entity with a known hardware profile, a lot of things become easy:

• An agent sends heavy reasoning to the GPU box and classification to the cheap CPU host, because it can see which is which.
• Agents on different machines see each other through Consciousness Server and coordinate by name.
• A machine going offline is visible to every agent, so pending work can be picked up elsewhere. Automatic re-routing: Planned.
• You can rent compute by adding a node — the rest of the fleet adopts it via its YAML descriptor.

Where this goes — exploratory directions

The paradigm generalises: anything with a controller, a state, and telemetry is a machine. None of the scenarios below ship today; they describe what the architecture enables once the right adapters exist. We mark them Planned or Exploratoryhonestly — flagged here so contributors and customers can shape the roadmap together.

Prototype shop / small factory

3D printers, plotters, CNC mills, laser cutters. An agent picks up a print queue, dispatches files to printers with the right material loaded, monitors job state, reports failures. Mixed deterministic execution (g-code goes to the printer verbatim) with non-deterministic decisions (which file first, which printer, what to do on a jam).Planned.

Research lab (biology)

Incubators, cytometers, sequencers. An agent reads experiment metadata from the LIMS, cross-references new results against shared memory in Consciousness Server ("how did the same condition behave in last week's run?"). Lab notebooks become a queryable corpus. Planned. Targets research environments first; clinical deployments need their own regulatory validation.

Energy infrastructure

PV panels, battery storage, EV chargers, server-room load. An agent balances when to charge the car, when to power servers, when to sell surplus to the grid. All locally, with no third-party cloud knowing your home-energy schedule. Exploratory.

Building / smart-home enterprise

HVAC, climate sensors, blinds, lighting. Agent learns occupancy patterns, suggests optimisations, never phones home to a vendor cloud.Exploratory.

Drones

Light-show choreography, infrastructure inspection (your own pipelines, towers, roofs), precision-agriculture monitoring. Each drone is a machine with telemetry; agents plan routes, react to wind, optimise battery rotation. Exploratory.

Private fleet / heavy equipment

Trucks, combines, excavators and other machines from different manufacturers under one owner. Today every brand pushes its own telematics cloud — a mixed-fleet owner ends up logging into a different portal for every brand, with telemetry, work history and predictive-maintenance data scattered across as many vendor clouds. One owner-controlled maintenance system (CMMS) instead, aware of every machine regardless of brand: collects telemetry locally, runs predictive maintenance on hardware the owner owns, keeps the full service history in one place — not across half a dozen manufacturer portals. Exploratory.