Live data from Hacker News

Herdr: Agent multiplexer that lives in your terminal

github.com

21–30 of 115 posts

Re: Herdr: Agent multiplexer that lives in your terminal

#21
post #6

Just use tmux no?

How would you know if a tab that isn't frontmost is waiting for input or complete or whatever?

You can achieve this with features that Tmux already have. Glued a tool that works:

https://gist.github.com/Enoch2090/5026c417f86ff6ff4fbe30c22b...

Re: Herdr: Agent multiplexer that lives in your terminal

#24
post #17

Earlier quoted context omitted.

You use an agentic harness which terminates with bell character[0]. This lights up tmux, clearly indicating that it's done. [0]: https://en.wikipedia.org/wiki/Bell_character

Does this mean adding instructions to AGENTS.md saying to end everything with the bell character? Or do harnesses have this in their settings somewhere?

I think generally harnesses have this. In claude code it's `"preferredNotifChannel": "terminal_bell"` in the settings.json, pi and opencode looks like you have to either add a hook yourself somewhere or use an extension.

Re: Herdr: Agent multiplexer that lives in your terminal

#25
post #10

Tried this for a couple days, but conductor.build is way better IME. Running _in_ the terminal is a flex, but doesn't actually bring any advantage.

I was just looking at conductor and was not very jazzed about the fact that it was running the agents directly on the host. Being able to launch from a terminal means this one can (hopefully) run from inside the sandboxing setup I use for coding agents.

Re: Herdr: Agent multiplexer that lives in your terminal

#29
post #23

This is way to complex... Why don't just use some harness which manages all that and give u a good UI?

I have been actively searching for such a thing for months without finding it.

Some are OS X only.

Some will not work well with VMs/isolated agents.

Currently using emdash, which is going in a great direction but somewhat new and buggy still.

Re: Herdr: Agent multiplexer that lives in your terminal

#30
post #3

does it support a setup where each agent can be in a different SSH session? or must they all run in the same place. it seems to support running a remote herdr over SSH but unclear if it can add remote agents (each agent has its own sandbox where its installed and you first SSH into it and then start the agent there)

Each work pane gives you a new terminal session, you can ssh into a remote and it will be kept alive. Should work fine.
Post reply on HN