Live data from Hacker News

Claude Code and Codex can have real-time conversation via Git

medium.com

51–60 of 95 posts

Re: Claude Code and Codex can have real-time conversation via Git

#54

Claude can directly drive Codex or Codex can drive Claude. Both already produce logs. It's unclear what value this intermediary brings.

It would be interesting if the agents could periodically check on themselves, whether the provider has routed prompts to dumber models as often happens with "adaptive reasoning" euphemisms.

If it detects that agent is dumb or has become dumb, it should terminate it and start again.

Re: Claude Code and Codex can have real-time conversation via Git

#57

I have started sandboxing all AI's in their own VM, and interfacing with them primarily through Jira and Git. It really is the only thing that makes sense. Completely sandbox'ed, and treated like the junior programmer who will do, literally, any dumb thing you tell them to do, as long as there is an Issue for it.

You might like what I'm working on at DBD: https://deepbluedynamics.com/nemesis

Just adding a menu this morning to allow re-attaching and session management.

Re: Claude Code and Codex can have real-time conversation via Git

#58

I have started sandboxing all AI's in their own VM, and interfacing with them primarily through Jira and Git. It really is the only thing that makes sense. Completely sandbox'ed, and treated like the junior programmer who will do, literally, any dumb thing you tell them to do, as long as there is an Issue for it.

Why are you using Jira and not GitHub issues?

One thing that is vital to managing agents this way, is the ability to easily create and use workflows, which can be easily kanban'ed. This is where I find Jira very comfortable - plus, I am already accustomed to managing Jira with both a workflow-driven Kanban, and jira-cli, the command-line interface.

So actually, firing off commands with jira-cli to get flows started by multiple agents watching their issues and putting their work in issue threads, is quite a nice interface .. and compatible with the other human-powered projects I'm managing this way, also.

Re: Claude Code and Codex can have real-time conversation via Git

#59

I have started sandboxing all AI's in their own VM, and interfacing with them primarily through Jira and Git. It really is the only thing that makes sense. Completely sandbox'ed, and treated like the junior programmer who will do, literally, any dumb thing you tell them to do, as long as there is an Issue for it.

How do you sandbox an agent? Docker?

Proxmox.

Re: Claude Code and Codex can have real-time conversation via Git

#60

I have started sandboxing all AI's in their own VM, and interfacing with them primarily through Jira and Git. It really is the only thing that makes sense. Completely sandbox'ed, and treated like the junior programmer who will do, literally, any dumb thing you tell them to do, as long as there is an Issue for it.

You might like what I'm working on at DBD: https://deepbluedynamics.com/nemesis Just adding a menu this morning to allow re-attaching and session management.

Yes, looks fun .. thanks for sharing. A lot of competition in this space though, of course ..
Post reply on HN