Summary Open Standards & Developer Access Advocates
This blog post announces Claude Code's integration in the Zed editor through an open Agent Client Protocol (ACP), emphasizing accessible developer tools and open-source licensing. The content advocates for open standards, developer choice, and community participation in technical development, with positive signals around freedom of expression, tool accessibility, and intellectual property rights for the developer community.
Zed is so great, I do wish they would focus just a little bit more on bringing the UI just a bit more up to parity with VS Code, I would switch full time.
I am sure Zed is great and I appreciate the effort put in to create it, but nowadays I just cannot imagine switching from VSCode to something else. In my limited understanding, none of the existing alternatives offer anything (and often misses at least something) truly innovative or anything else that VSCode extension wouldn't solve. On VSCode I have about 15 different profiles setup, each with different settings and dozens of extensions based on either a technology stack or a project - it would be really difficult to find a good reason to throw it all away. The idea of switching between IDEs does not appeal to me either. I do use Neovim a little bit too, but most of that usage time was spent on configuration.
My main issue with claude code is running multiple ones in parallel. I don't want to manually do all the git worktree stuff, I just want claude to handle it for me.
So if Zed automatically handles that (where there's a worktree per thread) I can see the appeal. Apart from that, I'm already using Tower to view the changes so I'm not really sure what the value here is.
I tried installing it, and got an error "can't load supported slash commands" – not sure what that means.
I want to try Zed but the Helix mode seems quite young. Vim mode sounds good, but i just can't move away from Helix mode. (oh and of course, my own modifications to Helix's input config)
My difficulty in finding editors that fit my desired input scheme kinda reminds me of the old pre-LSP days. Where you'd chose an editor based on it's language features. I wonder if we need some sort of common editor interface to allow these sort of text editing primitives to work in new editors, as it seems to be considerable friction.
One thing that still suffers is AI autocomplete. While I tried Zed's own solution and supermaven (now part of Cursor), I still find Cursor's AI autocomplete and predictions much more accurate (even pulling up a file via search is more accurate in Cursor).
I am glad to hear that Zed got a round of funding. https://zed.dev/blog/sequoia-backs-zed This will go a long way to creating real competition to Cursor in the form of a quality IDE not built on VSCode
What most of these comments are missing is the attempt at standardization and unification.
There are a lot of comments that people need X feature in order to switch to Y editor. While that may be true and your particular workflow requires certain features, what is overlooked is the survival pressure for editors.
It appears that our industry is moving towards adoption, sometimes mandatory, of AI coding agents. Regardless of your feelings on the topic, having good tooling to support this effort comes down to: switching costs, compatibility with existing editors, and a strong ecosystem of third party extensions.
While Cursor/Windsurf jumped the gun on bespoke editor integrations with LLMs - the adoption of MCP and other SDKs for coding agents means it's plug and play. The full feature set will be in every editor connected to every agent.
I think Zed wins on having the lowest switching costs for most developers. Paying down generic solutions like Agent Client Protocol (AC) now is a good strategy. It took multiple parties coming together for us to get TLS, OAuth 2.0, and ECMAScript.
I don't see why most editors should behave like hand crafted musical instruments when in reality they are much more akin to high quality knives in a kitchen (sure you have your favorite knife set and bring it from job to job, but at the end of the day you can be just as productive with a different knife when necessary).
I like Zed in concept.
I like Zed in the architectural and foundational aspects.
I want more tools like Zed to exist.
But, I find Zed challenging to adopt due to random nuances. First, settings management is a mixed bag and sometimes I just want a quick way to open the "settings.json" from the settings pane without fussing around. Then I'd like the "settings.json" to stay open (reopen) on a restart of Zed. Then I'd like the ability to use an LLM that doesn't have native tool calling support, which Zed seems to be the only app I've used that doesn't have a workaround. Then I'd like the UI to be a little easier to navigate as a new user, it feels a bit scattered and overwhelming at times.
I haven't used Zed much and I may give it another shot (soon), but it very much feels like a tool built by engineers for engineers... Which is great for power users, but seems not so great for new adopters.
I don't think the shortcomings are a blocker, but they are the reason I haven't adopted Zed. The shortcomings are just enough for me to take a step back and say "maybe I'll try again later".
It's great that Zed adding this very useful feature, but isn't this effectively cannibalize their own AI subscription plans? Why pay zed $20 when you already pay for claude code and can use it in the assistant panel? You might still want the edit prediction feature, but then why pay zed $20 when you can pay $10 github copilot and can use it to power zed's edit prediction feature?
As a VS Code + Claude Code user, I'm really excited to see progress here, because the official near-zero-config Claude Code IDE integration is... inflexible, at best.
What if I want to send a subset of my open editor panes to Claude Code? What if I want Claude Code to open diffs for its edited files in a specific area/window, and silently open that file so that I can multitask on other things without it taking focus when it's done thinking? What if I want keyboard shortcuts for specific slash commands, or to trigger a slash command from another task?
Having a robust open-source ecosystem that will let users fork and build customizable UI around coding agent experiences will make them even better, and the space will move even more quickly because the ecosystem won't split between different preferences for agent/model choice. It's an incredible time to be coding.
Glad to see this out so quickly. Like I said[0] on the Gemini announcement post, it feels like Zed is trying to get out of the business of iterating on agent logic and just let other people handle it. Any prompting secret sauce a) is trivial to copy, and b) gets eaten by the next model generation anyway. The capabilities of Claude Code, Codex, OpenCode, etc. seem to me to be converging.
Their landing page via Safari manages to crash my iPhone 11 Pro repeatedly, namely crashing Safari but also another app and the Bluetooth connections - had not seen that before so they are clearly innovative.
I love Zed but this has all the hallmarks of something being totally rushed out the door.
It works off the Claude Code SDK, which mean it doesn't support many of the built in slash commands - it doesn't support /compact, which is 100% necessary because when you use this implementation enough, you'll eventually get a "Prompt too long" error message with no ability to do anything about it. Since you can't see how far you are in the context window, it's a deal breaker, since you have to start a fresh chat and might run out of room before you can ask it to create a summary prompt for continuing.
There is no way to switch models that I can tell - I think it just picks up on your default model - and there is no way to switch to Plan mode, which has become absolutely crucial to my workflow.
I didn't see Zed picking up on problems reported in the IDE, it was defaulting to running 'tsc -b' in my directories.
At this point it's better to run a terminal inside Zed and work from there. The official response in the Zed Discord has been "talk to your local Anthropic rep" to get them to support Zed's Agent Client Protocol (ACP).
Also love Zed, but sigh, it's VC funded. We all know how this is going to end. Best VIM mode ever implemented in a (non vim) app. I use it as my 2nd editor (most of the time in Jetbrains products).
I just hope I'm wrong about the medium term impact of the VC funding but rushing AI AI AI out seems to be a sign of that rather than fixing fundamental issues that remain such as the ugly font rendering.
This interests me but they don't address practical Claude Code Opus 4.1 use at scale.
I have a $200/month Anthropic Max subscription that I use for help in exploring and coding my math research. As of now no AI model can compete with Opus 4.1 for helping me with my most challenging tasks. I try every one I can. Gemini 2.5 Pro is great for code review and a second opinion, but drives off the road when it takes the wheel.
I tried a $100/monthly plan and spent $20 in an hour the first time I went over; an API key is not a practical way to use Opus 4.1.
There are plenty of concerns using Clause Code in a terminal, that Zed could address. Mainly, I can't "see over AI's shoulder" so I need to also test. The most careful extension I coded was terminal sessions we could share as equal participants. Nevertheless, as a rule I'd attribute my relative success to just living with shortcomings, as if a "partner that snores". AI loses track of the current directory all the time, or forgets my variable naming and comment conventions? Just keep going, fix it later.
How can I get equivalent value to my Max plan, using Claude Code Opus 4.1 with Zed?
If they could add support for remote development (meaning the claude code instance runs on the remote server in the same folder that you have already opened as a remote/ssh project in Zed) and add a way to paste images in Zed and have them interpreted by CC on the server, this would really be a killer feature.
As someone who’s running a development agency I need to have tens of dev environments for different client projects running at the same time, and being able to switch between them multiple times every day (often from multiple client computers), so a remote server is the only way to go–I don’t want all of that stuff running on my Macs.
Nowadays I also have tens of CCs running on the dev server, switching between them using tmux, which works great, but the lack of support for pasting images through the terminal/ssh/tmux has been a real bummer. It would be great if Zed found a way to bridge that gap.
Fine. Cool step for Zed to push ACP, and I think this is the right direction for the IDE space.
But tbh if it’s not as frictionless as the Codex IDE extension in a Zed-skinned VSCode, it doesn’t matter.
Tried giving Claude and CC many chances, but the cognitive load of constantly managing a hard context window is DOA.
Codex w/gpt-5 is on par if not better than any of Anthropic’s solutions at this point, and the ubiquity (web, CLI, IDE) + UX consistency of Codex under one account/plan just dominates any marginal value of using a different model at a higher price.
Codex just works. Then it keeps working. Then it keeps working.
Any solution that wants to compete with OAI’s latest hostile takeover attempt has to match then beat on “unlimited/anywhere/frictionless” UX across platforms AND price ($200/mo all in).
I don’t see a good way out of this for most, except through major spend on playing catchup.
Guess that’s why Anthropic just raised again. Cursor is clearly trying to play, but they will always be a markup product until they launch their own SOTA model. Is Gemini still alive?
It's really interesting point of view. I'm one of those people who avoid using VSCode at any cost. It's slow, it's bloated, the UI is not great, and it's slowly being locked down by Microsoft.
If Zed would not exist, I would be using helix, neovim, or emacs as I did before.
I had to use VSCode for some projects in the past because it was what was available on the clients workstations...
I can't imagine having to use that laggy electron abomination all the time. For me Zed is sent from heaven, because my previously preferred editor (geany) hast basically zero developtment nowadays.
There is always a "better mousetrap", and there are those that continue to use the old one because they "know how it works and it's set up just the way I like it". And there are others that try every new mousetrap that hits the market. (and that's ok, not slighting either one)
I will say that I personally have never really gelled with VSCode no matter how much I try to customize it, it still is just a bit off. For me, it's like it's too much to be a simple editor like SublimeText or NeoVim, but not quite enough to be an IDE like IntelliJ or Visual Studio (full). It does just enough that I expect a bit more of it and it often fails to deliver. Right now I tend to just use 2 editors - one very simple one for viewing/editing text files and one IDE (currently IntelliJ) for coding in a project.
On topic - Zed is actually a really nice editor. It had some rough edges last time I tried it, but it's probably about time to give it another go.
That's unfortunate. I use Zed and I'm moving towards containerising my dev environment (using SSH remote dev to connect Zed to the container) because all this agentic stuff seems like a security nightmare. At the very least I want to restrict the blast radius to my repos dir.
I wanted to like VSCode but it has enough input latency on my machines that it's not that enjoyable when I'm "locked in". Also if I'm running a bunch of services in Docker on MacOS (which means they're running VMs sigh) the overhead of VSCode is just too much and the system starts swapping constantly grinding the whole thing to a halt. I also find configuring it a pain. Every configuration pane feels ad-hoc and not part of a holistic, configurable system. Emacs has lots of crusty bits and an annoying event loop that you have to really work around but is designed a lot more holistically than VSCode.
Zed to me feels like a great batteries-included editor and I still run it as my non-emacs alternate editor. I wish its configuration was a bit more discoverable (especially with configuring linters/formatters), but it's 95% of what I need 95% of the time.
Helix seems to have good LSP support from what I can tell? The only language I use at $WORK that doesn't have full support is GraphQL which lacks auto indent.
If you want to try something similar to Helix in emacs, there's meow-mode. While I'm not a helix user myself, it shouldn't be too difficult to get meow to work like helix.
I spent a while trying to set it up, as I share your general take on their ethos. Personally, I'm okay with a 'power user'-focused text editor, even! But the relative lack of syntax highlighting options got me to give up. Maybe I'm just spoiled from SublimeText's dope, complex, extensible system for specifying "contexts" in themes, but Zed was just nowhere near enough for me.
The keybinding system is also nuts if you turn on Vim mode, but I think I'd eventually get used to that. But functions need to be a different color than arguments, which need to be a different color than local variables... Just non-negotiable.
I look forward to trying it again sometime soon! The AI features seem rad, this included.
I was somewhat surprised to find that Zed still doesn't have a way to add your own local autocomplete AI using something like Ollama. Something like Qwen 2.5 coder at a tiny 1.5b parameters will work just fine for the stuff that I want. It runs fast and works when I'm between internet connections too.
I'd also like to see a company like Zed allow me to buy a license of their autocomplete AI model to run locally rather than renting and running it on their servers.
I'd also pay for something in the 10-15b parameter range that used more limited training data focused almost entirely on programming documentation and books along with professional business writing. Something with the coding knowledge of Qwen Coder combined with the professionalism and predictability of IBM Granite 3. I'd pay quite a lot for such an agent (especially if it got updates every couple of months that worked in new documentation, bugfixes, github threads, etc to keep the answers up-to-date).
I agree, I've fantasized about an editor with a truly pluggable editing model which is decoupled from the other parts.
Yi was kind of designed like this, I believe. You could compile in an emacs-like model, a vim-like model, or presumably make your own model.
I've used Helix and Kakoune in addition to Emacs and Vim, but dealing with the limitations/featureset/plugin treadmill gets a little tiring.
I have been following Zed, and it seems that they have rearchitected things to enable adding Helix mode and making the editing model a bit more modular, but it's still fairly new. They are fixing bugs pretty quickly. I will have to try it again.
I prefered Kakoune to Helix (it was more consistent). But to your point, being able to swap these things out more easily would let you choose an editor based on features, and not tradeoff between features and an ergonomic editing model.
Ironically you can use Ki inside of VSCode (and I know you can use Vim that way too), but VSCode is so darn bloated and slow...
It’s also great that they’re willing to risk that, in the name of a potentially better user experience. That’s what gets them to win in the long run, not building another walled garden.
Neovim can run in server mode, where other editors send it user input and then Neovim sends back the buffer. This is how I use vim in VSCode — not the Vim extension but the Neovim extension, which uses the real Neovim, which of course reads my Neovim config and plugins and makes them available to VSCode. So it seems like helix “just” needs a server mode, and then you can integrate it into any editor.
I wonder if Augment [1] are working on a Zed plugin.
I've been using Augment for more than a year in Jetbrains IDEs, and been very impressed by it, both the autocomplete and the Cursor-style agent. I've looked at Cursor and couldn't figure out why anyone needed to use a dedicated IDE when Augment exists as a plugin. Colleagues who have used Cursor have switched to Augment and say it's better.
Seems to me like Augment is an AI tool flying under most people's radar; not sure why it's not all over Hacker News.
Honestly, I’d love to know why that happens. Can you take a look at the logs? On Mac, you can do it through the Console app, and on Linux, through idevicesyslog.
> I don't see why most editors should behave like hand crafted musical instruments when in reality they are much more akin to high quality knives in a kitchen (sure you have your favorite knife set and bring it from job to job, but at the end of the day you can be just as productive with a different knife when necessary).
This is such a poor analogy. Yes, a good chef can make do with a different knife, but there is a reason why chefs pay for significantly higher quality knives, keep them sharpened, and treat them with diligence and care, than other kitchen tools. A blunt knife can actually be dangerous. Consequently, a lot of chefs buy knives that are effectively hand crafted / forged knives out of this relentless pursuit of quality.
> What most of these comments are missing is the attempt at standardization and unification.
> While that may be true and your particular workflow requires certain features, what is overlooked is the survival pressure for editors.
I think your general perception is not something I agree with. I want to use software I enjoy using. Programming is a creative exercise for me, and I want to use the tools I enjoy. If a tool is not enjoyable to use, I do not want to use it. Sometimes, productivity does increase enjoyment, but sometimes it doesn't. For example, arguably I would have been more productive in my Java days if I used Eclipse, but because the editor was so bad, I preferred to learn the APIs myself and use Sublime Text instead.
I also don't think I'm sympathetic to the survival of any particular editor. Software comes and goes, and sustainably built business models will prevail. All of the AI-first editors hinge on this being the right iteration of this technology, and we simply do not have a long enough timeframe or context to know if this is truly the best way to write code using AI. MCP/ACP, whatever else might be the best strategy for now, but I think it's too early for anyone to suggest that we've come to the right conclusion forever.
Zed does have a way to run LLMs without tool calling. From the agent pane, in the menu, select “new text thread”. I believe there’s a keyboard shortcut but I’m on my phone right now.
Article addresses right to work and favorable working conditions; blog emphasizes improved developer productivity and work experience
FW Ratio: 50%
Observable Facts
Blog describes improved conditions: 'Follow along in real-time as it edits across multiple files, with full syntax highlighting and language server support'
Post emphasizes reducing friction: 'when Claude Code is making changes across multiple files or refactoring complex logic, you may want to see the bigger picture and have more control'
Inferences
Visual feedback and control mechanisms improve working conditions for developers
Reducing friction with command-line interfaces supports better work experience
Article addresses privacy and protection from interference in personal matters; blog emphasizes developer control and transparency in code review process
FW Ratio: 50%
Observable Facts
Blog states developers can 'Review and approve granular changes in a multibuffer - accept or reject individual code hunks'
Post describes ability to see 'real-time as it edits across multiple files, with full syntax highlighting'
Inferences
Granular code review controls support developer autonomy over their workspace and code integrity
Transparency in change visibility respects developer privacy and control over personal development environment
Preamble addresses universal human dignity and equal rights; blog post is technical product announcement without direct engagement with universal dignity concepts
build 1ad9551+j7zs · deployed 2026-03-02 09:09 UTC · evaluated 2026-03-02 10:41:39 UTC
Support HN HRCB
Each evaluation uses real API credits. HN HRCB runs on donations — no ads, no paywalls.
If you find it useful, please consider helping keep it running.