[jamie_ca]

I'm buying into this workflow more the more I use it, but the real gamechanger is (a) parallel threads in worktrees, with (b) enough lifecycle hooks to treat them similarly to spinning up a VM.

Specifically for me that means that after I create a worktree I get some local config files copied over and Postgres duplicating my local dev and test databases so I can test in isolation, and then when I close out a worktree it deletes those databases.

The best at that that I've found is Conductor, but I can't use it at work because we only have Copilot and they're locked to a Claude/Codex backend. Arbor is close, but it's not under as active development and has a lot of rough edges. Opencode GUI has create hooks but not teardown.

If Zed can hook that up _and_ also keep its great editor roots, that'll definitely be a game changer.

[Charlieholtz]

Love to hear it! (Conductor founder here).

This is helpful to know - we're working on adding more agents, Copilot and OpenCode harnesses are among the most popular requests.

We also recently built an escape hatch. If you turn on Settings → Experimental → Big Terminal Mode you can create new terminals in the center panel (with ⌘⇧T) and use any agent you'd like (Copilot, OpenCode, etc). It isn't the best experience because you don't get notifications etc (yet), but at least it lets you use the harness you'd like until we build out the first-class UI for it.

Send me feedback anytime, I'm [e-mail].

[edf13]

Anyone know of a similar tool to conductor for Linux?

[jaen]

T3 Code should be similar: https://t3.codes/

[dcardamo]

https://paseo.sh/

[Atotalnoob]

I’m interested in these types of tools, but the biggest issue I am currently having in my workflow is manually verifying everything is working. Tests and stuff are nice, but typically if there is a bug, the AI agents enshrine it in th tests.

However with worktrees I am not really able to easily copy secrets, etc to run my app, ports conflict, I end up with a bunch of separate dbs and services, etc.

Does conductor help with this? Have you all found any useful ways of making this easier or more automated?

[shmoogy]

Conductor has a feature that lets you define a script to copy .env and other things as needed from main repo into new worktrees on creation.

I don't use it much anymore, but last I did I would run into port conflicts with docker projects.

[atonse]

I was an early user of conductor and used it a lot (like from maybe oct to Jan). But then there was some bug where maybe it wouldn’t release file descriptors or something where my laptop needed to be rebooted twice a day. So I stopped using it months ago.

But I’ve tried to reinstall it since and it just gets stuck in a weird infinite loop.

I liked conductor though. Hope you are able to fix those bugs and I can try again in a few weeks.

[BowBun]

Howdy, love your product. My coworker and I have literally been begging our coworkers to give it a try. To me, it was the key tool to 'get it' (coming from Cursor) when going from single threaded agentic dev to parallel agentic dev. Please keep up the great work.

[Nesco]

Conductor is really nice! A feature I would really like would be to be able to automatically configure “direnv allow” in the different shells as I use nix & direnv all the time

[laurels-marts]

Unless I misunderstand something but why not just roll a couple of helper shell scripts that create a new git worktree for you, copy over a local .env file (or any other config file) and populate it with ports/variables that are unique across all worktrees (to avoid collisions if you're on localhost, but you could also do this with Docker) and a helper script for tearing down a worktree after you've merged the changes back into main. I'm even supplying unique chrome debug ports and unique temp user data dirs for isolated automated testing in chrome via chrome devtools mcp. Like, I'm not sure why an external library/tool is needed for this.

[jamie_ca]

Oh, yeah 100% I'm putting up scripts for them, the conductor hook is "run the one script" for setup/teardown.

The difference is removing friction, having a UI that shows me what's set up, that I don't need to hit the filesystem or git status to check in, that gives me _direct_ access to a shell/etc in that worktree path.

[Klaster_1]

In VSCode, I use https://github.com/jackiotyu/git-worktree-manager for the same purpose - the extension has before create/before destroy WT hooks which you can run anything from. Mine symlinks workspace file from main checkout, installs packages and copies over some files. Very handy.

[sheremetyev]

I've built multi-agent workflow on JJ workspaces - independent from specific agent. You can run Codex, Claude or anything else - https://www.visualjj.com/learn/parallel-ai-agents

[sbysb]

You should check out Ouijit [1] - I use it regularly for work and it's nice because it focuses on the environment that you want, and just gives you a shell that you can use any tooling in, as well as VM isolation per worktree if needed.

[1]: https://github.com/ouijit/ouijit

[rtfeldman]

> The best at that that I've found is Conductor, but I can't use it at work because we only have Copilot and they're locked to a Claude/Codex backend.

FYI, you can use Copilot directly in Zed!

[maximilianroos]

self-promotion, but check out worktrunk.dev

by far the most popular worktree manager

[jdkoeck]

No need for any AI-specific tool, this is exactly what devcontainer is for! Just tell your agent to use devcontainer up (and docker compose down the other way).

[donmcronald]

Devcontainers always disappointed me. The sales pitch is that everyone uses the same container, but that's not accurate. Everyone builds a container from the same config and it'll be similar, but it takes a ton of effort to make sure it's identical.

The idea that a devcontainer gets built on-demand instead of checked out like 'docker pull ..." has always felt weird to me. It's so close to being awesome, but ends up being barely useful.

Or maybe I'm wrong. Is there a way to checkout an immutable devcontainer?

[TingPing]

Just specify “image” https://containers.dev/implementors/json_reference/

[kippinsula]

tried parallel agents for a sprint and bounced off it. the worktree dance is fine, real blocker for us was test data isolation. scoped postgres schemas per branch worked, but reasoning about which agent broke teh shared migration when three of them touch it got old fast. we just run one agent at a time now and go for a walk.

[anthony-eid]

We support create git worktree hooks too

[saturn_vk]

Is there an example of this?

[jamie_ca]

The worktree create hook is documented https://zed.dev/docs/tasks?highlight=hook#hooks

And then I guess setting up tasks for the cleanup part, but it'd be great to see that get automated too so I don't need to remember it.