Live data from Hacker News

Gemini CLI will stop working from June 18, 2026

developers.googleblog.com

211–220 of 224 posts

Re: Gemini CLI will stop working from June 18, 2026

#211

Earlier quoted context omitted.

> I think people project their values in situations that don't have place for them and get upset That is a very useful bit of wisdom that one can overlook easily, but once articulated can explain a fair bot behaviour.

> bot behavior Freudian slip?

I meant a fair bit; but a fair bot will just do as well these days.

Re: Gemini CLI will stop working from June 18, 2026

#212

Earlier quoted context omitted.

By unifying the billing and quota systems, as well as providing better integration, I presume The Antigravity harness is by far better than the gemini-cli one. Antigravity also offers models other than Gemini as well. When you say Antigravity, you think of a platform whereas when you say Gemini you think of the model It's great that gemini-cli is open-source, but that also comes with a bunch of ai-generated issues an…

OSS == "great... but... will impede development"?

Yes, since the former part relates to me as the individual (as I get the benefits of an open source project)

The latter is about the contributors that can no longer reap the benefits of OSS, since the amount of noise (e.g. low quality contributions, false-positives etc) leads to wasted time and effort to keep up with the flood

Were you to decide to one day file a genuine bug report or make a pull request, big chances that you will never get a response (1.5k issues, 329 pull requests open as of now). It's a Frankenstein('s monster) of a project from all perspectives, which is a shame, since I'm rather fond of the interface

Re: Gemini CLI will stop working from June 18, 2026

#214

Earlier quoted context omitted.

Reminds me of the Microsoft days circa 2010 when Microsoft published half a dozen media players (Zune!), word processors, email clients, etc.

I think this is a systemic problem of an industry where gross margin is 80% or higher, so you can plow all that extra money into superfluous headcount tasked with objectives of questionable business value. It’s a curse of riches, if you will. The rest of us living on 15 to 30% margins need to think a little harder about what we do and why.

FWIW, what you will see at times in the HF world is a firm will want to get into a strategy and build competing teams. It lights a fire under both. It diversifies the risk. You can select winner and move some people over from loser. And if they both work, they both work.

It isn't a crazy idea if the opportunity is large enough to make the larger investment required worth it.

The problem I see in applying this to products is it can be very confusing for clients.

Re: Gemini CLI will stop working from June 18, 2026

#215

As much as I like Gemini CLI and don’t like them shutting it down, I think it’s good some of the offerings are getting unified. There was too much fragmentation in the google offering and this is making it a tiny bit better.

You really like Gemini CLI? imo among all the model zoo provider, it's really the worse, and they didn't even update the models in it for days after each release, had to resort to weird hacks via MITM.

Re: Gemini CLI will stop working from June 18, 2026

#216

This is why most devs I know have stopped building anything serious on top of Googles AI tools. You cant build a workflow around something that gets renamed or killed every 6 months. Anthropic and OpenAI atleast understand that developer trust requires stability, Google still treats their AI devtools like consumer products. Ship it, rebrand it, kill it.

We still use multiple Google Ultra accounts because no choice for adversarial, but `gemini-3.1-pro-preview` is just offline so often, it's confusing how it's even possible, as in I'd say it's probably 80% uptime all-in, it's really a catastrophe overall, especially that Google was kinda known to be "always up".

Re: Gemini CLI will stop working from June 18, 2026

#217

It’s a good decision. If an IDE can do everything that a CLI does and it surely can, then I fail to see the point of a CLI. It’s not like an IDE can’t emulate everything a CLI does but better, faster, and more interactive. It’s not like one does not need to read code either. Besides, what about session management? What about configuring agents, especially for multi-agent orchestration? The list can go on. The point i…

I don't want to use a full AI IDE, I've been using Gemini CLI a lot and it works better for my workflows to bring my own IDE and use Gemini CLI alongside it. My assumption is others are having annoyances for the same reason.

Re: Gemini CLI will stop working from June 18, 2026

#219

Earlier quoted context omitted.

By unifying the billing and quota systems, as well as providing better integration, I presume The Antigravity harness is by far better than the gemini-cli one. Antigravity also offers models other than Gemini as well. When you say Antigravity, you think of a platform whereas when you say Gemini you think of the model It's great that gemini-cli is open-source, but that also comes with a bunch of ai-generated issues an…

When you say Antigravity, I think of floating around on a space ship.

You failed the shibboleth. Real programmers think of xkcd.

Re: Gemini CLI will stop working from June 18, 2026

#220
post #22

I read through the docs. There is no mention of whether programmatic usage or Agent Client Protocol will continue be supported in Antigravity CLI.

People are saying it doesn't have ACP at all. We don't know if that's an intentional decision or a temporary gap.

I don't think it's happening because Antigravity's concurrent core architecture is incompatible with ACP. For example Antigravity supports running multiple agent and process threads in the background while keeping the main thread free for conversation. ACP can't really support that.

To put it in ad speak, ACP is too basic for how advanced the agy harness is

Post reply on HN