I was just commenting yesterday (https://news.ycombinator.com/item?id=50367546) how I really like Conductor except that it doesn't work so well if you want to work across multiple repositories.
I guess that's the kick I needed to dig into the alternatives.
At Command Center (https://cc.dev), we've just started working on cross repo support. (Can have agents run over a group of workspaces in different projects)
Our main selling point: we focus on features for iteration, code quality, and human understanding to get PRs to production quality faster.
There's also "residential data center" proxies you can buy, it sound weird but it's ISPs selling some of their regular residential IP space to proxy companies so they don't look like data center IPs.
I'm currently using https://www.conductor.build/ for working on multiple projects at the same time with git worktrees and my Claude subscription. The annoying part is that if I have a frontend repository and a backend repository I have to tell each session "talk to this workspace to adapt the backend" if I'm working on the frontend. I wish they had better support for multiple repos in one session.
Separately I'm evaluating https://ampcode.com/ which is very polished, but I feel like the diff-reading part is not very prominent there which I find a bit odd. After watching many of their videos I feel like that's because they are opinionated on this not being necessary any more as the models are good enough. I kind of agree, but still like to give it a last glance before committing.
Claude Code (and Codex too I believe?) can message other sessions these days. I just run one session per repo and they talk to each other directly when the frontend needs something from the backend and vice versa. This has removed most of that back and forth for me and eliminated the need for orchestration tools.
These days I’m getting so many 1Password prompts for agents pulling env variables out of it and with very little context of what is being accessed by who (The dialog 1Password shows is pretty bad) that it would be very easy for something to slip in there.
> I’m getting so many 1Password prompts for agents pulling env variables out of it and with very little context of what is being accessed by who
This is a one-sentence horror story. I almost can't believe someone would let this happen, unless the 1Password account is not important (highly unlikely).
I know it sounds bad, but it’s the reality for most people, just like permission prompts at every corner and after each macOS / app update (“Your screenshot app is watching your screen”, no shit, that’s why I installed it).
The dirty little secret of our industry is that everyone runs agents with full disk access on their machines as there's no good way to sandbox it. This also precisely why Apple posted a newsroom article a few days ago about this topic: https://developer.apple.com/news/?id=p6zjojqw
Blaming this on the user is a bit like blaming someone for doing their banking on their regular day to day computer instead of an air gapped machine.
Yeah, I don’t know about that. We use VDI and dedicated agent accounts. Sort of like I’ve got my super user account for production server access via a different VDI, now I’ve got my -agent account for the agent VDI.
> Just get the source code of Forgejo, audit it thoroughly and run an instance of that.
Or use the open-source version that is used by a lot of big companies and enterprises and has the enterprise features they actually need. Some of these will also have their own security team and would be flagging security issues to Gitlab in a hopefully responsible way.
There's no such thing as "just get the source and make sure there's no security issues". If it would be that easy don't you think Forgejo would've already done that?
No, no. They’re right. It’s a very “Linux” thing to do. Applies to Unix as well? Yes. But it is most definitely what one comes to expect of Linux, not Mac.
I guess that's the kick I needed to dig into the alternatives.
reply