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

Parallel agents in Zed

zed.dev

Post reply on HN
Print view View original

111–120 of 178 posts

Re: Parallel agents in Zed

#111

Post by Atotalnoob »

Charlieholtz wrote: post #102
jamie_ca wrote: post #7

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…

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 bec…

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?

Re: Parallel agents in Zed

#112

Post by BowBun »

Charlieholtz wrote: post #102
jamie_ca wrote: post #7

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…

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 bec…

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.

Re: Parallel agents in Zed

#113

Post by a012 »

caterama wrote: post #106
hsaliak wrote: post #101

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 am exactly the same, except I am really excited about this update! It’s not so much “in parallel” but being able to easily jump between threads. It allows me to dive into misc investigations in a side thread without derailing some main context where I’m doing the main editing.

I also have this workflow, it’s like you’re on the side quests or on the main story; those are not necessarily in parallel

Re: Parallel agents in Zed

#114

Post by somnium_sn »

cpill wrote: post #51
2001zhaozhao wrote: post #4

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…

yeah, but they don't support a lot of the features Claude does like MCP integration. we've booked this up to logfire (telemetry provider) and it's a game changer when doing optimisation or diagnosis of bugs. plugins and skills also missing. but it is nice to switch between provider easily

Little historic sidenote: Zed was the first MCP client next to Claude Desktop

Re: Parallel agents in Zed

#115

Post by brikym »

verse wrote: post #8

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

It will also pull more users in. I don't want to be looking at code. I want more of a codex style app where it's easy to shove all my projects in one place and context switch endlessly.

Re: Parallel agents in Zed

#116

Post by alanwreath »

I wonder if you could use something like vLLM and have these subagents max out your local gpu. I’ve been looking for using a local model because I’m tired of rate limits of the cloud and also would really like to make use of my local gpu when I’m working (5090h even if it’s not on my computer I’m typing on.

Re: Parallel agents in Zed

#117

Post by Klaster_1 »

jamie_ca wrote: post #7

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…

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.

Re: Parallel agents in Zed

#118

Post by pastel8739 »

anthony-eid wrote: post #48
RonanSoleste wrote: post #42

Earlier quoted context omitted.

A proper git implementation. I end up doing things in the terminal tab because its faster than the ui or is more clear. The basics are good but thats about it.

What git features are you missing? We've been adding a ton recently

I use zed every day, but the git view is still buggy and unreliable for me. It often chooses the wrong folder---a subfolder rather than the root of my git project---and shows that there are no changes. And sometimes, even when the right folder is selected, it will still incorrectly say there are no changes.

Another bug is that clicking on new files in the git UI doesn't bring up their diff---you need to click them twice to open the file. I'd like to have those files included in the diff view just like other files are.

I'd love for there to be an easier way to get to the "view file history" view---I didn't realize that it existed until I tried searching for it. I'd love a "line history" view like GitLens has, as well.

Re: Parallel agents in Zed

#119

Post by pastel8739 »

submeta wrote: post #45

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 set…

I must be missing something crucial in my obsidian setup. What is Obsidian without its frontend? For me it's just a bunch of markdown files.

Re: Parallel agents in Zed

#120

Post by TingPing »

donmcronald wrote: post #98
jdkoeck wrote: post #92

Earlier quoted context omitted.

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).

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 b…

Just specify “image” https://containers.dev/implementors/json_reference/
Post reply on HN