Deploy Your Omnigent

Everything in the previous sections runs on your laptop. That's the fastest way to get started, but when you want your omnigent accessible from your phone, shareable with teammates, or running while your laptop sleeps, you need to deploy.

This section covers Omnigent's architecture and the deployment options for each component.

Architecture

Omnigent has three components:

Omnigent architecture

Server

The server is the central coordinator. It manages:

Runner

The runner executes omnigent loops. It manages the harness (Claude Code, Codex, Claude SDK, etc.), runs tools, and streams events back to the server over WebSocket.

By default, the runner is a process on your laptop:

omni host <server-url>

This is why your local Claude Code or Codex installation "just works." The runner has direct access to your machine's tools, files, and credentials.

The runner can also be hosted in the cloud as a cloud runner, so your omnigent executes in a cloud container instead of on your local machine. Supported hosting platforms:

More platforms are on the way.

UI

The web UI, terminal UI, and mobile UI all talk to the server. They never talk to the runner directly. This means:

Deploy the server to the cloud

The server and runner deploy independently. Moving the server to a cloud host gives you:

See Cloud platforms and Docker for ways to host it.

Host the runner in the cloud

Moving the runner to a cloud runner gives you: