# Where it runs You run the control plane. Agents run wherever you have checkouts — your machine or a hosted fleet. Rendered page: https://agentrelay.com/docs/factory/where-it-runs Markdown endpoint: https://agentrelay.com/docs/factory/markdown/where-it-runs.md --- Factory splits into two halves: the **control plane** that decides what to work on, and the **agents** that do the work in a real checkout. The control plane is yours. Where the agents run is a choice. ## Local agents ```bash factory start --mode live # --backend internal is the default ``` The control plane and every agent run on one machine, against the checkouts in your `clonePaths`. It reuses a relay broker already running for your workspace and starts one if there isn't. This is the whole loop on one box — the simplest thing that works. ## Remote agents on a fleet ```bash factory start --mode live --backend relay ``` The control plane still runs on your machine, but agents are placed onto fleet nodes through the hosted engine. Placement picks a live node advertising the capability the work needs; the node runs the agent in its own mapped checkout; the orchestrator detects exits by reconciling its tracked agents against the engine roster. Use this when the work shouldn't run on a laptop — bigger checkouts, longer builds, machines that stay up. ### Bringing a node online Mint an enrollment token from the Fleet page in the dashboard, then, on the machine: ```bash # once per machine — redeem the token for durable node credentials agent-relay cloud enroll --token ocl_node_enr_… # each boot agent-relay node up ``` `agent-relay node up` auto-discovers an `agent-relay.ts` in the working directory, which just re-exports the node definition: ```ts export { default } from '@agent-relay/factory/node'; ``` The node reads `factory.node.json` for its `workspaceId`, capabilities, and the `clonePaths` map naming the checkouts it services. Each mapped repo is advertised as a `repo: