Just use tmux no?
This works much better than tmux.
Herdr: Agent multiplexer that lives in your terminal
61–70 of 115 posts
Re: Herdr: Agent multiplexer that lives in your terminal
#62[flagged]
Re: Herdr: Agent multiplexer that lives in your terminal
#63if you prefer to self host but with a gui there is https://github.com/kdlbs/kandev
Re: Herdr: Agent multiplexer that lives in your terminal
#64Unlike Cmux, Herder will not call out to multiple web services upon start-up.
Re: Herdr: Agent multiplexer that lives in your terminal
#65Multiplexing the agents is clearly the first obvious pain point, but the other one I keep encountering after this is visibility: with multiple agents running, it becomes difficult to see what each of them is doing, what program did they call, and where they are getting stuck until they complete or fail. Is there any information from Herdr about what each agent is up to beyond the output? Or does it just concentrate o…
I’ve been using herdr for about a week. There is visibility into which terminals need attention and you can set up workspaces to organize it. I’ve enjoyed it so far though the key bindings are all over the place - likely due to it trying to avoid existing bindings.
Re: Herdr: Agent multiplexer that lives in your terminal
#66Once you get it set up, Emacs is a pretty damn good "agent" multiplexer as well. I use agent-shell with Projectile on Doom Emacs as my main workflow these days, and it works very well even if I have 6 projects open or whatever. Claude and Codex are also both quite good at working with Emacs as well. Depending on your isolation/sandboxing strategy, they can either run commands against your session via emacsclient (a b…
Please share any useful guides and/or resources for agentic development with Emacs!
Re: Herdr: Agent multiplexer that lives in your terminal
#67How do people use terminal multiplexers together with vim? Ctrl+B is so hardwired in my fingers for scrolling back one screen that there's no way I'm remapping that one in vim itself. So then you have to remap that in your terminal multiplexer, while at the same time there's a bunch of people saying never change the leader key... Curious what vim users especially do about this?
Change the tmux leader to ctrl-space, problem fixed!
I'd recommend using Page Up and Page Down, but this seems like a much better solution.
Re: Herdr: Agent multiplexer that lives in your terminal
#68has anybody figured out how to get this to open a fixed layout? I'm using tmuxp to do this easily with tmux but would switch to this pretty quickly if it was easy to get my layout over. It's really nice. It's like zellij without the bloat (but with different ai bloat that doesn't seem to drag down performance at all and isn't in your face unless you want it in your face)
Re: Herdr: Agent multiplexer that lives in your terminal
#69Re: Herdr: Agent multiplexer that lives in your terminal
#70Multiplexing the agents is clearly the first obvious pain point, but the other one I keep encountering after this is visibility: with multiple agents running, it becomes difficult to see what each of them is doing, what program did they call, and where they are getting stuck until they complete or fail. Is there any information from Herdr about what each agent is up to beyond the output? Or does it just concentrate o…
I’ve been using herdr for about a week. There is visibility into which terminals need attention and you can set up workspaces to organize it. I’ve enjoyed it so far though the key bindings are all over the place - likely due to it trying to avoid existing bindings.
[flagged]