Skip to content
ModelReins ModelReins Docs

Multi-Machine

For larger deployments, run the coordinator on one machine and workers on as many machines as you want.

Architecture

Section titled “Architecture”
┌─────────────────┐
│   Coordinator    │ ← Dashboard, job queue, worker registry
│  (server-1:7420) │
└────────┬────────┘
         │
    ┌────┼────────────┐
    │    │             │
┌───┴──┐ ┌───┴──┐ ┌───┴──┐
│Worker│ │Worker│ │Worker│
│Ollama│ │Claude│ │Laptop│
└──────┘ └──────┘ └──────┘

Coordinator setup

Section titled “Coordinator setup”

On the coordinator machine, follow the Single Server guide to deploy the coordinator. Make sure it binds to 0.0.0.0 so worker machines can reach it.

Worker setup

Section titled “Worker setup”

On each worker machine, install the Companion app (see above) and point it at the coordinator URL. The Companion handles provider detection, heartbeats, and job polling automatically.

Security

Section titled “Security”
  • Always use MODELREINS_API_KEY to authenticate workers.
  • Use HTTPS (reverse proxy) for coordinator access over the internet.
  • Workers only need outbound access to the coordinator and their provider APIs.

Scaling

Section titled “Scaling”

Add workers at any time — they register automatically. Remove workers by stopping the process. The coordinator requeues any in-progress jobs from disconnected workers.

Companion App on spare machines

Section titled “Companion App on spare machines”

The easiest way to add machines to the mesh — download the Companion installer and point it at your coordinator:

During setup, enter your coordinator URL (e.g. http://coordinator-host:7420) and an API key. The Companion handles registration, heartbeats, and auto-reconnect.

See Companion App for details.