I was surprised people were so willing to jump to closed source IDEs just for access to coding agents. The trade-off you pay for tight integration between the IDE and the coding agent is lock-in because the barrier to switching IDEs is nontrivial.
Your coding environment stands a lower chance of disruption when you use an open source IDE with a CLI agent. Yes it's slightly annoying to separate the agent from the IDE but the benefit is that it's much easier to switch between Claude Code, Codex, Gemini CLI (now antigravity CLI), etc which means you can more easily benefit from pricing and coding performance differences which seem to change monthly.
Closed source IDEs are if anything the norm: Visual Studio, Android Studio, XCode, IntelliJ, CLion, PyCharm, etc... Even in the "fancy text editor" category things like Sublime were always popular enough.
Closed source?
IntelliJ: https://github.com/JetBrains/intellij-community
PyCharm: https://github.com/JetBrains/intellij-community/tree/master/...
Android Studio: https://android.googlesource.com/platform/tools/adt/idea/+/r...
Yes, they might offer extended proprietary editions/plugins in addition, but the IDEs themselves are open source.
Oh, this is great!
I've filed bugs with JetBrains before and had them take months getting to my ticket, often with multiple hand-offs between team members; being able to provide a potential fix should make the process much faster.
None of these are the "norm". The IDEs OC mentioned all have a much larger install base.
Do all of those installed on my various machines for the express purpose of a last resort of building some obscure crap about once a couple years count? Because of course I have them installed.. somewhere. And of course I wouldn't imagine using that crap daily.
The funny part is that Gemini-Cli is open-source, and now they are getting rid of it for Antigravity CLI.. which is not open-source. Fun.
If you care about keeping your development environment free from corporate lockin and control you should also avoid closed source CLIs and use open-weight models.
Antigravity is just a vs code (more correctly: codeium) skin with Google telemetry and agent Integration. You can switch back to Microsoft's or cursor's flavor in minutes.
It isn't anymore, though, that's kind of the whole point of the article.
They just renamed it to antigravity ide. I don't think that product is deprecated.
Thing is, I recognize this UI. It looks identical to the VS Code "Agents Window" feature. Except it's... a standalone app, for some reason.
Fwiw, the (mostly) closed source jetbrains IDEs support multiple models with their coding agents, byok, and using different agents like Claude Code via ACP
Fair, the important distinction is agent-agnostic rather than open-source. There are other risks to using a closed source editor but those are mostly orthogonal to this discussion.
amen!!
this is why i've built all of my setup using a dotfiles-like approach with the explicit intention of always being agent/model-agnostic: https://github.com/ma08/botfiles
the key insight is that if you own the context layer and keep your skills, hooks etc. portable enough, it's actually very easy to swtich agents at will (even mid-task)
> barrier to switching IDEs is nontrivial
That was definitely true in the hand-crafted code era, but I've found all the agentic-type things to be basically the same? Even if you're fairly involved in the code, you're still just mostly reading diffs and editing the odd line, the kind of basic work that's the same across all modern editors.
Do we still need an IDE though? I am very happy with Claude Code last 6 months. I can totally see why Google got rid of everything, but the dialog box. Perhaps it was stupid to do that without warning, but ultimately this is the future.
I find this comment mind-boggling; in an honest confusion, not insulting way. I use Claude Code (and desktop) on a daily basis; but I can't even imagine doing anything complex without being able to see the code.
There seems two kinds of developers
1. Developers that create the mess and don't have to deal with the consequences
2. Developers that fix the mess and have to deal with the consequences
I've noticed that the former category is significantly more pro AI than the latter
I admit I look at the code less and less now. But when I do want that I just ask Claude to show me the code verbatim. It is almost always faster than click in IDE because it greps with insane speed. After all, when it's fully AI-generated it's sort of someone else's codebase from my perspective, I end up grepping through it the same way it does.
Gradually I moved to asking questions about the code instead, something like "if X and Y, will Z still hold? did we not forget to check this?" I realized that this is what I am doing in my head when looking at the code. And Claude understands well enough what I mean and checks it.
What I found mind-blowing though is that surprisingly often it says me something like "while looking this up for you I think found a potential bug, would you like me to quickly check it?" or "I noticed that actually when X and Y true, Z holds indeed, but I believe there is a rare situation (...) when we don't want Z because it makes zero sense, what do you think?"
> I can't even imagine doing anything complex without being able to see the code
I mean, it's totally possible they just aren't doing anything complex.
That being said, for even the simplest stuff I do I benefit from looking at the code, making changes etc.
[flagged]