Full-screen TUI monitor

Watch and steer a run, without leaving the terminal.

A detached run used to be a black box you poked at with JSON. The monitor gives you a live cockpit: logs, a timeline, and approval gates in place, plus the power to grab the wheel when an agent gets stuck.

$ smithers monitor 7f3a

Why this exists

A run you cannot see is a run you cannot trust.

You kick off a long job in the background and then fly blind: polling status commands, grepping JSON, guessing whether it is stuck or just slow, and unable to step in when an agent goes down the wrong path.

What it shows

The whole run, at a glance.

☰ logs

Live output

Streamed logs as steps run, so you see what the agent is doing the moment it does it.

⧗ timeline

Where it is

Every step and its state in one column. Done, running, queued, failed, at a glance.

✓ approvals

Gates in place

When a run pauses for a human answer, approve or reject it right here. It detects the gate for you.

⛘ hijack

Grab the wheel

An agent stuck in a loop? Drop into hijack mode and steer it back on course without killing the run.

⤺ events

Full history

Scroll back through the run's events, even for a run that started before you opened the monitor.

⌨ keys

Keyboard-native

Built on OpenTUI. Move, toggle, approve, and switch modes without ever reaching for a mouse.

How to open it

One command, any run.

Watch a specific run

Point it at any run id and drop straight into the cockpit.

$ smithers monitor 7f3a

Launch and watch at once

Start a workflow interactively and the monitor opens on it as it runs.

$ smithers up --interactive

Stop flying blind on your own runs.

Open the cockpit on any run and watch it, approve it, or steer it, all from the terminal.

$ smithers monitor