Interact with your Omnigent

Once an agent is running, Omnigent gives you multiple real-time surfaces: terminal, web UI, mobile, and desktop. They all connect to the same persistent, shareable session, so you can start work in one place and keep going anywhere.

Starting a session

omni claude                          # Claude Code
omni codex                           # Codex
omni run agent.yaml                  # custom omnigent
omni run ./my-agent/                 # directory with config.yaml

omni claude and omni codex launch an existing coding agent with Omnigent's UI. No YAML needed. See the Coding Agent tutorial.

omni run starts a custom omnigent from a YAML config. See Custom Agents for how to write one.

CLI overrides

Override executor values at runtime without editing the YAML:

omni run agent.yaml --harness codex --model gpt-4.1-mini

The --harness and --model flags map directly to the executor block. This lets you reuse the same config across different LLM backends.

Sessions and conversations

A session is a conversation. Every message, tool call, and file change lives in one continuous thread. Sessions are the core unit of work in Omnigent, and three properties make them useful:

What happens when you run

Omnigent spins up a local server (localhost:6767 by default) and gives you four ways to interact with your agent:

All four surfaces connect to the same session in real time.

Browser-first mode

If you prefer to work entirely in the browser without a terminal, start the server and host daemon separately:

omni server start   # start the local server + web UI in the background
omni host           # (separate terminal) register this machine as a host

Now open http://localhost:6767 in your browser and work from there. The terminal is optional.