Running Claude Code and Codex side by side, in one place

The problem with one terminal per agent

Once you use coding agents seriously, you stop having one of them. You have Claude Code on one repository and Codex on another; a refactor running in the background while you review a diff; three things queued for after lunch. A terminal tab per agent handles this badly: scroll back far enough and the history is gone, closing the tab kills the work, and nothing tells you which of the four tabs is the one that died.

One workbench, many sessions

Clootee treats a session as the unit of work. Each session has its own workspace, its own engine and its own history, and they run at the same time.

• A queue per session. Line up several tasks and let them run in order instead of babysitting them one at a time.
• Interject without losing the run. Pause, reorder, or drop a message into a task that is already running.
• Switching sessions stops nothing. Looking at session B does not interrupt session A.
• Both engines, same UI. Claude Code and Codex are installed from the same screen and driven with the same controls, so choosing between them is a per-session decision, not a change of tooling.

Why transparency matters more as the work gets longer

When an agent edits your files for forty minutes, “done” is not enough information. Clootee keeps the full trace of what happened:

• Reasoning, streamed as it is produced, collapsible once read.
• Every tool call with its complete input and output — the exact command, the exact diff, the exact path. Nothing is compressed into a reassuring sentence.
• Timings and token counts per step, which is how you find out that one retry loop cost more than the rest of the task combined.
• A file manager per workspace, so you can read and edit the files being changed right next to the session changing them.

And when it goes wrong

Long runs fail in ways short ones do not: the engine process dies, the engine returns nothing at all, or everything looks alive but nothing has happened for far longer than this task should take. Clootee surfaces each of those as its own state, with a reason and a next step. That is the difference between a task you can leave running and one you have to sit and watch.

Where your data lives

Everything runs on your machine. API keys, engine settings, session history and traces are written to the data/ folder next to the program. There is no Clootee account and no telemetry, so there is nothing to opt out of. The trade is the one you would expect from a local tool: you are responsible for the machine it runs on — and because Clootee runs the agent with permission prompts bypassed, keep it bound to 127.0.0.1 and reach it over an SSH tunnel or VPN rather than exposing it.

Try it on one project first

The install costs nothing and touches nothing: a portable Node inside its own folder, no changes to your PATH or your system Node. Point one session at a real repository, queue two small tasks, and watch the tool calls go by. That is the honest way to tell whether this fits how you work.