Zed should focus on basics. When it focuses on basics Zed is good.

https://github.com/zed-industries/zed/discussions/54150 failing to show newly created files and declining to provide a refresh button, instead adding a polling backend, breaks Zed on WSL.

Why a new version control system? Why not git, jj, or another existing system?

Their ACP integration is good (finally), at least with Codex. For when I want to be near the code, I prefer it now over TUIs or the Codex app. It feels much more immediate that way. Sticking to the basics will kill them IMO. They have been pitching themselves as agent-native for a while btw.

And the workflow they are describing in the post sounds amazing, I‘ve been wishing for that. It‘s orthogonal to CVS, no? You can still make PRs. But, crucially, you can loop people in early on, when it matters the most.

Sounds like a side-effect of being VC-backed. Like what the ex GitHub CEO went on to build (Entire). Unnecessary.

A non-existent problem that nobody asked to solve...

This makes me uncomfortable.

Maybe I’m pessimistic, but I think this just gives micro-managers the data they need to micro-manage you. It invites people to scrutinize the process, instead of the results.

Not once have I wished to review a colleague’s conversation with an AI. I want to review finished work.

I look at this and I can only imagine layoffs being justified with “bad prompt quality”. An incident retrospective broadcasting your agent conversations to the entire company, with people speculating where you should have put the “make no mistakes”.

It’s a shame, really, because I like Zed as an editor, but I can’t bring myself to support them if this is the direction they’re choosing.

Not only this. I'm also shuddering at the thought of how much more noise this adds which can only be filtered through LLMs.

Indeed, I want the information between commits for myself, so I see the utility. But I don't want people observing every keystroke.

The way I’m seeing AI used by organizations is to produce process slop: tickets, summaries, docs, etc. rather than drive process change and optimization, or enable individuals to be more effective within the organization.

It's also delusional to think you can find that one edit that was really useful but you forgot to commit but then deleted in another giant commit.

As anyone who's ever tried to split a days worth of work apart with `git add -p` is well aware.

It may be feasible with a million agents, but they could remember what they typed three hours ago anyhow.

I start to sound like a Jujutsu fanboy but...

Jujutsu already does this. I had agent screwing up changeset over couple hour long session and it took one shell command to split on pieces with longer pause.

The only downside is that because of Jujutsu snapshots it can't be used inside sandbox (since all jj commands are mutating)

Looks like a great feature/product/functionality. I hope that Zed editor will make it work with LLMs/agents that run in the terminal, not just the Zen Agent itself. Is it even possible? I use OMP.sh agent running in Zed terminal.

It supports anything with ACP. So it can actually run Codex and Claude Code, not just the Zed Agent.

Looks like omp supports ACP, so all you have to do is specify a Custom Agent in Zed and it should just work.

https://omp.sh/docs/acp

https://zed.dev/docs/ai/external-agents

This is the killer Zed feature, IMO, that they support almost any agent via extensions. I deleted Cursor but still use the agent via Zed because it’s a lot nicer experience, Zed never had popups telling me Grok is half off. I also use OpenRouter and Zed.dev with it, that’s three providers out of dozens that it supports.

Exactly. The more competitive the space is, the more important it is that products purposefully support 3rd-party providers. Now that people are increasingly switching from Anthropic/OpenAI for inference reseellers and on-prem compute, transparency and portability will be the new values, not being slightly better than the next agent or model.

I use this every day — https://zed.dev/blog/terminal-threads

What problem does this product solve?

This local history has saved my bacon on occasion. E.g. when I went too long without committing and something silly overwrote the file I was working on. Or because I did something silly with git. Then it is nice that there is still an independent backup elsewhere with different failure modes.

Like a branch on the server?

i think a system that uses git and file system artifacts (txt/md/xml files whatever preference) is much better. eng teams need to define their artifacts, eg plan file, reqs etc whatever is needed and important to that team. the agent convo itself doesn’t add much value IMO and adds unnecessary bloat.

I have fallen in love with Zed.

This is a big unsolved dev tooling problem. Glad someone competent is working on it.

Yes, but it saps away the time that could be used to improve zed.

Or it’s actively used to improve Zed faster (or more efficiently).

zed is open source, you are free to improve it on your own

Yes, it is open source, and I am not saying they should not do it. Chromium is also open source, but if they added too much nonsensical AI functionality, I would be upset. I am free to improve it on my own, but that does not mean I cannot express how I feel.

I have not gone to the Zed repository and created an issue telling them to stop developing DeltaDB because it takes away the maintainers’ time.

Is this closed source?

Basically what IntelliJ calls local history. It is a feature that has saved my bacon. https://www.jetbrains.com/help/idea/local-history.html

Similar, but not as polished, also exists in VSCode and derivatives, named the same way. Definitely saved me a few times as well.

Yes, I concur. Local History is wonderful; nice to see Zed getting its own version.

Ooooh, this is cool. I was unaware of this. Thanks for the link.

It should work with github inbetween commits, that i may use. Right now I'm using staging as an in bewteen in a dangerous way.