Agent-Manager: A Tmux TUI for Running Claude Code, Codex and OpenCode

I run three or four coding agents at once and the part that eats my time isn't the coding, it's that I can't tell what state any of them is in without tabbing through every terminal. One of them is usually sitting on a permission prompt I never saw.

agent-manager is a Go binary on top of tmux. No config file, no daemon, no server. Every agent shows up in one list with a live status, grouped by the project it's running in. Status comes from reading the pane, so adding a CLI is a few lines of regex in a toml file rather than an integration.

The keystroke I use constantly is space: press it on an agent, type, enter, and the prompt lands in that agent's pane without attaching. Press it on a project row and you get a new agent already working on what you typed. ctrl+r opens what an agent changed as whole files with the diff highlighted, and a comment left on a line is sent back to that agent as a prompt.

Sessions are plain tmux sessions, so quitting the manager leaves everything running and v reattaches a session with its conversation intact.

I built it for four agents and most days I use it with one. Still rough in places, and I'd like to hear what breaks for you.

How is this different from https://github.com/asheshgoplani/agent-deck ?

This looks really good, but for me the timing of seeing agent-manager is bad: I read about the similar Herdr on HN several days ago and I have completely changed my dev setup for the better.

I have always been a traditional simple command line tool kind of developer (I am an old man, old habbits die hard!) but I recommend at least a one day experiment with tools like agent-manager and/or Herdr that integrate tools like Claude Code and OpenCode into an integrated work environment.

I have been hacking on my own Emacs based agentic coding and work environment (so much fun!) but my recent experience with Herdr has been much more productive.

Anyway, the docs for agent-manager look good, I look forward to reading HNer’s experience with it.

Isn't this what https://www.superlogical.com/ supposed to accomplish?

Finding it a bit wild that I've been working on something somewhat similar for a few weeks now.