| ▲ | Herdr: Agent multiplexer that lives in your terminal(github.com) |
| 69 points by mzehrer 6 hours ago | 35 comments |
| |
|
| ▲ | ricardobeat 29 minutes ago | parent | next [-] |
| The utility is not obvious, but I've been using herdr for a few weeks after a friend recommended it, and it's been a great tool. I had about a dozen different terminal windows, each one with multiple tabs, which was becoming a mess to manage; multiple agents and harnesses running that I could only inspect by remote access/VNC away from home. With this, I can keep things more organized (project workspaces, tabs), because it's backed by a persistent process, I can ssh into the machine, with tailscale, run herdr and see all active sessions, do some debugging and one-off prompts. Even better, I can do that from my phone and iPad using Prompt/Termius. It gives me the best part of 'xxclaw' harnesses with none of the complexity. |
|
| ▲ | crashabr 20 minutes ago | parent | prev | next [-] |
| How does it compare with https://github.com/agent-of-empires/agent-of-empires |
|
| ▲ | mintflow 20 minutes ago | parent | prev | next [-] |
| Will people really need a bunch of different agents?
Even using two codex session for different project make me feel a bit overwhelmed, or may be i just old |
|
| ▲ | JSR_FDED 2 hours ago | parent | prev | next [-] |
| 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? |
| |
| ▲ | coldtea 33 minutes ago | parent | next [-] | | >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. Give it a month and whatever you remapped will be "hardwired" too. In any case, no reason to keep Ctrl-B in tmux either, you can remap that just as well. | |
| ▲ | pyr0hu 2 hours ago | parent | prev [-] | | 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 |
|
|
| ▲ | hagen8 an hour ago | parent | prev | next [-] |
| This is way to complex... Why don't just use some harness which manages all that and give u a good UI? |
| |
| ▲ | dagss 34 minutes ago | parent | next [-] | | 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. | | |
| ▲ | dandaka 28 minutes ago | parent [-] | | What is your top chart? I am using GUI harnesses from model providers and not happy with any of them. |
| |
| ▲ | ricardobeat 36 minutes ago | parent | prev [-] | | for example…? |
|
|
| ▲ | mst98 3 hours ago | parent | prev | next [-] |
| nice, not dissimilar to what i built for https://github.com/storozhenko98/beehive |
| |
| ▲ | w4yai 2 hours ago | parent [-] | | 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 4 hours ago | parent | prev | next [-] |
| 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) |
| |
| ▲ | ricardobeat 34 minutes ago | parent | next [-] | | Each work pane gives you a new terminal session, you can ssh into a remote and it will be kept alive. Should work fine. | |
| ▲ | scirob 4 hours ago | parent | prev | next [-] | | 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 | | | |
| ▲ | steinroe 4 hours ago | parent | prev [-] | | afaik, you should be able to use named session to achieve this: https://herdr.dev/docs/persistence-remote/ |
|
|
| ▲ | felooboolooomba an hour ago | parent | prev | next [-] |
| At least one of us needs to up our dosage. |
|
| ▲ | scubbo 3 hours ago | parent | prev | next [-] |
| 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. |
| |
| ▲ | zavec an hour ago | parent | next [-] | | 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. | |
| ▲ | xyzsparetimexyz 3 hours ago | parent | prev | next [-] | | 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 3 hours ago | parent [-] | | I'm using `opencode --web`. Running over HTTP means I can use it comfortably on my phone with Tailscale. |
| |
| ▲ | mellosouls 23 minutes ago | parent | prev | next [-] | | mac only. closed source. | |
| ▲ | Quarrel an hour ago | parent | prev [-] | | conductor.build is Mac only .. |
|
|
| ▲ | progx 4 hours ago | parent | prev | next [-] |
| I need a shepherd for my terminals. |
|
| ▲ | andrijaskontra 4 hours ago | parent | prev [-] |
| Just use tmux no? |
| |
| ▲ | ZeelRajodiya 43 minutes ago | parent | next [-] | | How about running this inside tmux? | |
| ▲ | boxed 4 hours ago | parent | prev [-] | | How would you know if a tab that isn't frontmost is waiting for input or complete or whatever? | | |
| ▲ | rocqua 3 hours ago | parent | next [-] | | 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. | |
| ▲ | enoch2090 an hour ago | parent | prev | next [-] | | You can achieve this with features that Tmux already have. Glued a tool that works: https://gist.github.com/Enoch2090/5026c417f86ff6ff4fbe30c22b... | |
| ▲ | baalimago 4 hours ago | parent | prev [-] | | 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 2 hours ago | parent [-] | | 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? | | |
| ▲ | zavec an hour ago | parent | next [-] | | 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. | |
| ▲ | baalimago 2 hours ago | parent | prev [-] | | 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. |
|
|
|
|
