Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Agent-talk: Enabling coding agents to work together

github.com

Post reply on HN
Print view View original

21–28 of 28 posts

Re: Agent-talk: Enabling coding agents to work together

#21

Post by fragmede »

andai wrote: post #9
tcdent wrote: post #5

Earlier quoted context omitted.

I do something very similar. With some hacky string matching you can detect wether a window is available for reception and get past that. I desire a more robust system which injects the events into the harness directly, but haven't found a way that works across systems. https://github.com/tcdent/dotfiles/blob/main/bin/agent-messa...

I hooked up Claude Code's "stop" hook to a frog croak, so I know when it's done. I'm guessing the same hooks could be used to ... Okay I guess there isn't a User Typed But Didn't Send Yet hook... Hmm... I heard earlier there's a T3 harness which somehow wrangles other harnesses as one big meta harness, but I haven't checked it out yet.

I had my stop hook playing a sound, but I have a couple of them running at the same time so I'd have up figure out which one stopped, so I had Claude change it so the stop hook told me which one stopped.

Re: Agent-talk: Enabling coding agents to work together

#23

Post by andai »

fragmede wrote: post #21
andai wrote: post #9

Earlier quoted context omitted.

I hooked up Claude Code's "stop" hook to a frog croak, so I know when it's done. I'm guessing the same hooks could be used to ... Okay I guess there isn't a User Typed But Didn't Send Yet hook... Hmm... I heard earlier there's a T3 harness which somehow wrangles other harnesses as one big meta harness, but I haven't checked it out yet.

I had my stop hook playing a sound, but I have a couple of them running at the same time so I'd have up figure out which one stopped, so I had Claude change it so the stop hook told me which one stopped.

With a TTS? Or you mean just using different sounds. Considering both of those options right now.

A while back on my phone all the damn notifications sounded the same, so I just made a couple of recordings of myself saying the name of each app and set those as the notifications.

Re: Agent-talk: Enabling coding agents to work together

#24

Post by cromka »

thepoet wrote: post #18

Interestingly we did a version of a shared communication bus over MCP here https://github.com/instavm/murmur The idea being mostly to use all of the coding agent subscriptions which are much cheaper than API access in order to delegate tasks, break down into chunks and distribute or even the standard coder/reviewer pattern.

This seems like a much more robust solution compared to one posted here. Do you actively work on developing this?

Re: Agent-talk: Enabling coding agents to work together

#25

Post by thepoet »

cromka wrote: post #24
thepoet wrote: post #18

Interestingly we did a version of a shared communication bus over MCP here https://github.com/instavm/murmur The idea being mostly to use all of the coding agent subscriptions which are much cheaper than API access in order to delegate tasks, break down into chunks and distribute or even the standard coder/reviewer pattern.

This seems like a much more robust solution compared to one posted here. Do you actively work on developing this?

Yes, we have been using this internally too. If you use it and encounter any bugs or have ideas for improvement, please file it. I will have a look.

Re: Agent-talk: Enabling coding agents to work together

#26

Post by killix »

xhluca wrote: post #12
ramoz wrote: post #10

The friction of agents having to monitor CLI is just too annoying right now Thus, this is ultimately: 1. a harness problem (or harness orchestrator) 2. a protocol problem With 1. Claude Code does this very well - yet most OSS harness are not great or do naive subagent tasking making hard even for a parent to talk to the child. But we can then rely on harness orchestrators - Herdr does this very well, so does the Code…

I thought about MCP, but found that having it as a Claude skill is much simpler (since it can be installed as a plugin, and only depends on md files and also doesn't need to run a server all the time). The nice thing about claude code is that the monitor can directly be spin up to run in the background and listen to new messages via retalk receive --follow, so every time there's a new message it will push it direclty…

[flagged]

Re: Agent-talk: Enabling coding agents to work together

#27

Post by HappySweeney »

tcdent wrote: post #5
HappySweeney wrote: post #3

I have a more primitive setup where I use Gemini, Claude, and Codex at the same time and cultivate expert contexts. Each of them lives in their own tmux session so they can read each other's terminals and prompt each other. One issue that I keep stamping out is that another instance will paste a prompt and hit enter in the middle of my typing.

I do something very similar. With some hacky string matching you can detect wether a window is available for reception and get past that. I desire a more robust system which injects the events into the harness directly, but haven't found a way that works across systems. https://github.com/tcdent/dotfiles/blob/main/bin/agent-messa...

The hacky string matching is what I started with, but there was always new ghost text. I turned suggested prompts off which helped, but idle hooks plus ensuring the terminal doesn't change over a half second has done the trick so far, and I don't have to keep chasing new ghost text.

Re: Agent-talk: Enabling coding agents to work together

#28

Post by fragmede »

andai wrote: post #23
fragmede wrote: post #21

Earlier quoted context omitted.

I had my stop hook playing a sound, but I have a couple of them running at the same time so I'd have up figure out which one stopped, so I had Claude change it so the stop hook told me which one stopped.

With a TTS? Or you mean just using different sounds. Considering both of those options right now. A while back on my phone all the damn notifications sounded the same, so I just made a couple of recordings of myself saying the name of each app and set those as the notifications.

With TTS. It tells me what it just finished doing. That's pretty clever on your phone!
Post reply on HN