Set up OpenRig on this VM by following the exe.dev recipe at https://exe.dev/deploy/openrig.md from top to bottom.

The recipe's example VM name is my-openrig. This VM's name is the output of `hostname`: use it wherever the recipe writes my-openrig. Skip the step that creates the VM; you are on it.

You are done when all of these are true. Check each one yourself:
- OpenRig 0.7.6 with its daemon and kernel (operator, advisor and queue worker), started by systemd.
- Claude Code and Codex connected to exe.dev's LLM integration, with no API key on the VM.
- A two-agent team in `~/project`: a Claude Code builder and a Codex reviewer, each in its own tmux session.
- Teams that were running come back after a reboot and resume their conversations.

Read the whole recipe, including the closed details. For setup, follow
"Install by hand" only, skipping VM creation; the walkthrough above it is
for the owner. Do not run the restore, update or Pi instructions.
Install exactly @openrig/cli@0.7.6. Never attach to a tmux session; read
agents with `rig capture`. Do not send the team work, and do not run
`rig down`. Keep the VM private: never run share set-public or bind the
daemon beyond 127.0.0.1. On an existing VM, ask before replacing
~/.openrig, ~/rigs/pair or ~/project, or Claude Code or Codex settings
that aren't exe.dev's.
Verify: `rig doctor` reports no failures; openrig.service is enabled
and active; `rig status` says `Kernel: ready`; `rig ps --nodes --rig
pair` shows both seats `run`, each with a last observed model. Do not
reboot.
Finish with the two SSH commands from "Meet your team", using this VM's
name, and suggest the owner give the builder a first task.

Finish with the URLs I should open.