Herdr: Agent multiplexer that lives in your terminal

(github.com)

54 points | by mzehrer 3 hours ago

6 comments

  • JSR_FDED 18 minutes ago
    How 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?

    • pyr0hu 12 minutes ago
      As a vim user, I just remap C+B to C+A. It's much easier on the fingers too. Issue arises when I ssh somewhere that doesn't have the leader remapped but that's usually pretty rare when I have to vim in a tmux session on a remote host so not really an issue
  • mst98 1 hour ago
    nice, not dissimilar to what i built for https://github.com/storozhenko98/beehive
    • w4yai 41 minutes ago
      I'd suggest adding a few screenshots on the Github README, otherwise I wouldn't have enough attention to imagine how it looks. I had to go to the website to appreciate your work, otherwise I'm like "what is it?"
  • nok22kon 2 hours ago
    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)

    • scirob 2 hours ago
      Same question.

      I usually have one local clause orchestrating multiple remote Claude in different tmux . And then another orchester and remote vm worker sin tmux for another repo etc...

      It gets a bit hard to keep the overview but I don't want to give up my parallelism, your too might help

      • _def 1 hour ago
        Interesting, how is this orchestration set up?
        • messh 1 hour ago
          One way is to use something like https://shellbox.dev - you start new boxes and manage it all through ssh, icl agent running inside
    • steinroe 2 hours ago
      afaik, you should be able to use named session to achieve this: https://herdr.dev/docs/persistence-remote/
  • andrijaskontra 2 hours ago
    Just use tmux no?
    • boxed 2 hours ago
      How would you know if a tab that isn't frontmost is waiting for input or complete or whatever?
      • rocqua 1 hour ago
        Someone else suggested the bell character. But you can also just set tmux pane names or color. Which you can also do from your agent harnass.
      • baalimago 1 hour ago
        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

        • timwis 32 minutes ago
          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?
          • baalimago 13 minutes ago
            Depends on the harness I imagine. If there's some sort of "post run" hook I'm sure it can be added there. Or, if the harness is open source, a PR to add it would work too.
  • scubbo 1 hour ago
    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.
    • xyzsparetimexyz 1 hour ago
      Running in the terminal means I can access it via ssh on my phone (& tailscale). Do any of the other solutions let you do this?
      • yoavm 1 hour ago
        I'm using `opencode --web`. Running over HTTP means I can use it comfortably on my phone with Tailscale.
  • progx 1 hour ago
    I need a shepherd for my terminals.