Parallel agents in Zed

It's pretty clear by this point that everyone is going towards parallel agents and worktrees, but TBH I am surprised to see an offering from Zed, seeing how heavy they lean into being editor-heavy and having AI features be strictly optional.

The key advantages Zed has are being agent-agnostic (so not a first party UI like Claude/Codex/Cursor Desktop), supporting multiple repositories on the same agent via creating a worktree for each automatically, and having a high quality custom agent UI rather than wrapping over CLIs (I've used their IDE's agent UI in the past and it's great). AFAIK, this is the first mainstream tool that supports all of these features.

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.

I find parallel agents to be an exception rather than a norm. Maybe I’m the problem? For those exceptional cases, opening a few more terminals gets the job done. It’s unclear to me if this needs to be the primary workflow. My brain naturally does better on deep work on one problem..

I tried Zed and was really convinced that I could use it full-time, but the lack of extensions (TODO highlight, TabOut) + other QoL (line number goto as easy as VSCode + tab filter like another comment said).

I also thought it was odd that I can't configure the font size in the git commit message editor.

On recent additions, the dev container integration was great.

Rooting for you Zed!

Warp launched something similar a week or so ago, but the Zed implementation I find a lot more logical. Will give Zed another try, as I’m overdue for my monthly “maybe I should try this terminal/IDE” itch.

I personally don't love the idea of the default layout pushing aside my code and filetree to make space for AI tools

I really like Zed, I use it every day. But, if I'd seen this layout when I first installed, I never would have taken it seriously

I imagine this will push some new users away

Yesterday, I determined to move to Zed because they weren't pushing this stuff :(

I would love to unleash parallel agents, but I am still checking every single edit while enforcing minimal, stateless, modular code, and I have the AI check in with me before writing the next file.

A lot of times, I find it has incredibly stupid ideas and tends to make the code very messy. I would love to figure out how to stop that from happening automatically.

The upside of checking in on the code, though, is that I can come up with smart directions for the AI from both a product and tech perspective. This is especially helpful when the dumb suggestions add a lot of complexity.

I think it's like when a product person asks for a new feature, or when a founder building their own product selects which feature is smarter to build and how.

I really want to like Zed, but for some reason the way it interfaces with the TypeScript language server is dog slow compared to VS Code and its derivatives.

Zed is probably the best text editor in the last 10 years. It has quirks, but it is insanely powerful and capable out of the box. I don't even bother trying to setup Neovim because of Zed. They let people for PRs for missing vim features for their vim emulation, and its insanely capable.

I hope someday they get the funding they deserve, because it has insane potential. It's why I subscribe to their pay plan, even if I dont use it all the time, I want them to succeed.

Love Zed for my personal projects at home with Openrouter. But I cant use it at work as I'm forced to use claude code at work and find the VSCode+claude code combo better. I know zed has claudecode integration, but I found it to be very weak compared to zedagent+claudemodel. Has this improved?

What I want is a stateful file-writing layer that is aware of all clients (aka agents and humans) and their activity. It provides its own locking mechanisms, and prevents agents from overwriting each others work. That way you could have multiple agents operating on the same codebase, without having to futz with worktrees and all that.

I loved zed for over 1 year, told for everybody to use it, because it was so fast and great.

But now using claude-code,gemini-cli,codex,etc it just seems less relevant. Just opened nvim with lazyvim and it feels nice, since I'm in terminal anyway it just feels more natural.

Still have zed opened, still like it but I guess honeymoon is over.

I've used Zed since the very beginning and I remain a fan. Its LLM integration so far has been a lot more pleasant than what I see in others and the editor is perfectly usable without using LLMs.

Its multi buffer and speed sound trivial but using anything else feels wrong now.

I'm having a hard time adjusting to the Project Panel on the right (and, at least for me, hidden by default) - seems like they're trying to bury the concept of a 'file'?

It's certainly interesting though, and I'll give it some time - the post says "It feels more natural once you've spent a little time with it"

I liked the idea of the new layout with the agent thread on the left, it goes hand-in-hand with having multiple threads that are easy to switch between and running concurrently, but I switched back because my file tree disappeared and I couldn't easily see how to add it back

I just installed Zed last night and enabled vim mode, can't wait to try this!

This is great! I love Zed, but when I came across Superset I stopped using Zed. Maybe no I will go back to it

If Cursor is worth $60bn, how much is Zed worth?

Funny how Zed's tagline is

  Love your editor again
  Zed is a minimal code editor crafted for speed and collaboration with humans and AI.

I remember when Zed's main thing was "collaborative" editing. Not as profitable as AI I suppose.

I've been a Sublime Text user for years, then a VSCode for years. Been trying Zed for the past couple weeks and it has been a good experience.

Zed might have a fighting chance against VS Code now that it's million extensions are quickly becoming irrelevant since agents do all the coding.

What's needed today is a nice way to orchestrate agents and do some small manual edits there and there to the code.

Becoming more and more useful by teh day. Love to see it.

I like Zed but the defaults for tabs (CTRL+Tab and CTRL+Shift+Tab step you through some diabolical tab selector in what is allegedly (but not really) recency order instead of just left/right. It really made me question their sanity.

Does this work with ACP?

I gave zed agent another shot today, and it couldn't run bash commands, so back to opencode I go.

Love Zed.

Is this any different from a setup where I use a terminal with tabs and splits, running my favorite editor in one or more panes, and several agents (Claude Code and Codex) in several other panes and tabs?

Edit: Although I can integrate an agent in NeoVim, I don’t do it. I want to use my editor solely for that purpose, while the rest (versioning, agentic coding, git client, etc.) is done in the terminal. My NeoVim setup is simple and fast, which is why I prefer it over any other IDE or editor. Especially with the native package manager in the latest version. I also replaced BBEdit by installing Neovide, a GUI version of NeoVim. It starts in a split second and is incredibly smooth and fast. And it’s so enjoyable to work with that I use it as my preferred frontend to Obsidian.

[dead]

[dead]

[dead]

The worktree part is the easy half. Running parallel Claude Code subagents, the bottleneck is never "can they run without stomping each other's files." That's solved the moment each one has its own checkout.

The hard problem is architectural consistency. Agent A renames a type to X. Agent B, in a different worktree, independently renames the same type to Y because neither saw the other's decision. When you merge, neither worktree is "wrong" but the code is incoherent. You need either a shared decision log that every agent reads before starting, or an orchestrator that hands out scope narrow enough that no two agents can collide.

Zed's post is solving filesystem-level parallelism. The harder coordination problem is semantic, and that's where time savings from parallelization go to die.