yoanwaidev

The note skips one detail. Enter focuses by default, and Settings can swap it with attach. A double click still focuses a session either way.

I tried multiple TUIs and desktop apps, but none had a fast, keyboard driven workflow to quickly dispatch agents, see who needs my attention, and most importantly, review and iterate on the Ai's changes through comments. So, I built one. It quickly gained traction, and people have already started contributing to help me build it! It works with Gemini, Codex, Hermes, Claude, OpenCode, Pi, Command-code and more to come, works on Linux, macOS, and WSL.

as an anthropic employee, do you trust the benchmarks?

Almost finished my weekly limit today! I am more excited from the usage reset!

Same instinct locally with git worktrees: one agent per worktree so they do not thrash the same checkout. Cloud VMs buy isolation and scale; worktrees buy cheap isolation when you already have a machine. I end up using both patterns depending on whether the bottleneck is compute or just not stepping on each other.

You're not, and this won't convert you. The reason I stay in a terminal is that the agents already live in one, so a TUI is a view over what's running rather than a second place things live. If your agent already runs in a GUI, that argument doesn't apply to you.

Different scope, as far as I can tell from their site: they describe a multiplexer for all work, spanning remote hosts, sandboxes, CI, production systems and shared terminals. This is a Go binary that drives tmux on the machine you're already on, and every session it creates is an ordinary tmux session you can attach to without it. Much smaller bet, and it stops where tmux stops.

To be clear on the GUI point, since my last reply here answered a different question: this is a terminal tool and it won't convert you. The reason I stay in one is that the agents already live in terminals, so the manager is a view over what's running rather than a second place things live.

herdr's a whole runtime, own multiplexer, plugins, socket api. mine sits on tmux and doesn't try to replace it, sessions stay normal tmux sessions.

overlap on the status sidebar is real. two things I lean on that I couldn't find a key for over there: space on a blocked agent types the answer into its pane without attaching, and ctrl+r opens its repo as full-file diffs where a comment on a line goes back to that agent as a prompt. herdr's socket api can push text into a pane, so the first one is scriptable at least. correct me if I missed something.

mouse and windows, herdr's ahead.

agent-deck was the first one I actually tried to adopt, landed a couple of commits in it. wanted it to be the one.

what I kept missing was answering an agent without attaching to it. so space on a blocked one, type, enter, and it lands in that pane. on a project row it spawns a new agent already working on what you typed. the other half is review, ctrl+r opens what it changed as whole files with the diff tinted, c comments a line, C sends the notes into the pane.

deck does plenty I don't, worktrees, cost, forking. different bets.

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.