Coordinate multiple coding agents from one terminal

Corgi gives you a single terminal view for launching several coding agents and checking what each one is doing.

Done with CodexClaude Code· Intermediate

What they did
They installed Corgi with its curl-based setup and used it with Claude Code, Codex, Pi, and OpenCode. From that same interface, Ctrl-T can open a new session or bring back an existing one tied to their accounts. The tool marks each agent with a status such as working, needs you, unread, or clear, and it keeps those sessions available while the user works elsewhere.
How it went
The product page says it can surface activity, per-workspace resource and token use, file edits, and worktrees. It does not include numbers, usage examples, or a detailed explanation of link labeling.
Tips
It is available on macOS, Linux, and WSL. For image pasting over SSH, the page points to Ghostty Nightly.

Try it yourself with Codex

Set up a terminal workflow for [project path] where I can run [task 1], [task 2], and [task 3] in parallel with coding agents. Create one git worktree per task, start a Codex or Claude Code session in each worktree, and give me a single view that shows the worktree name, the agent attached to it, and whether that agent is working, needs my input, unread, or clear. Before you delete any branch or worktree, or before you submit anything, stop and ask for my approval.

Fill in the [brackets]. Agents can make mistakes, so review anything before it is sent, paid or deleted.

Read the original on corgi.computer ↗

Get 3 agent uses like this every morning

With the day's top AI news. Free, and one click to unsubscribe.