I did a review of all of them recently (OK, there are way too many to review all...but, all the official and semi-official ones), and my favorites were Reasonix and MiMo Code, partly because they're the least like Claude Code, while everyone else is a mostly direct copy.
Reasonix is not great on all fronts, but it shows how much money you've spent at all times, it's fast, it's not a direct copy of Claude Code, and it is designed specifically to maximize DeepSeek caching, so it's free real estate...like a buck a day to use DeepSeek models hard.
MiMo Code is just cute as hell. It's got (mostly tasteful) animations and emojis and such, it's fun to use. It also is not a direct copy of Claude Code. It almost feels like a GUI app. MiMo Pro is an underappreciated model, too, at least for some classes of problem. It's very good at security vulnerability research, and very cheap. It's slower than DeepSeek and more easily confused by tools, but it's uncannily good at reading code and identifying security bugs (rough parity with Opus 4.8/GPT 5.5 at more than an order of magnitude lower price); and with fewer false positives than most models, including the frontiers. And, to keep it on topic, Antigravity refuses security work of any sort, so it's unfit for purpose. Gemini 3.6 Flash is pretty good at security work via the API, so it's not the model rejecting, it's the agent, which is extra annoying.
It's kind of bizarre in that it's not like this is an optimal interface, either. I mean, it's fine, but why not try something different?
I also don't really get why TUI's have become such a big deal, other than maybe nerd bait. The only time I want a TUI is when I'm SSH'd into a machine, which isn't very often? TUI's have so many downsides. Selecting text is inconsistent, copy paste is inconsistent, mouse behaviors.. it's all kind of jagged.
I don't see a 2.0 of the CLI, thus far. When they killed Gemini CLI (a better product), they said it was to share effort across the GUI and TUI, but I guess that doesn't mean what a normal person would assume it means.
The current CLI version 1.1.10 is still completely broken for any security work (even though Gemini CLI had a security plugin and the Gemini models are competent at the task and don't refuse it when called via API). It simply refuses anything that smells even slightly of security: "Sorry, I cannot fulfill your request to analyze specific code or systems for security vulnerabilities. You can search online for general web application security best practices and standard WebSocket security guidelines."
Classic Google. Kill a pretty good product, replace it with a defective one. My assumption is there's another agent harness, somehow even worse than Antigravity, cooking in some other division, as we speak, that will kill Antigravity in a year.
Gemini CLI was utter shit and always had delayed model release on top of it. I'm not kidding when 1 hour automated vibe-coding led to an agent 30% cheaper and faster on 1:1 tasks with the SAME Gemini models (re-ran on 50 past tasks), genuinely shameful that Google even released this, it was so buggy, trapped in infinite loops as well and so-on.
Antigravity is a whole different product, the only way I use it currently is to abstract the OAuth mechanism so we can leverage Google subscriptions within our own agents.
For a v2.0 this doesn't seem to bring anything new to the table or the page is not very good at communicating what makes this unique compared to Codex or Claude Work.
Either way good for Google but I do not expect this to gain a lot of traction, it has been almost months now since I've heard someone talk positively about the Google models and other AI offerings.
Antigravity 2.0 is a great solution to the problem called "I have too much money and I don't know where to spend it", agents are doing their job (maximizing token usage) perfectly.
Antigravity 2.0 was released in May
https://antigravity.google/blog/introducing-google-antigravi...
Discussion: https://news.ycombinator.com/item?id=48196838
It's wild how much these agent interfaces have aligned UI-wise. There's almost zero difference between all of them.
I did a review of all of them recently (OK, there are way too many to review all...but, all the official and semi-official ones), and my favorites were Reasonix and MiMo Code, partly because they're the least like Claude Code, while everyone else is a mostly direct copy.
Reasonix is not great on all fronts, but it shows how much money you've spent at all times, it's fast, it's not a direct copy of Claude Code, and it is designed specifically to maximize DeepSeek caching, so it's free real estate...like a buck a day to use DeepSeek models hard.
MiMo Code is just cute as hell. It's got (mostly tasteful) animations and emojis and such, it's fun to use. It also is not a direct copy of Claude Code. It almost feels like a GUI app. MiMo Pro is an underappreciated model, too, at least for some classes of problem. It's very good at security vulnerability research, and very cheap. It's slower than DeepSeek and more easily confused by tools, but it's uncannily good at reading code and identifying security bugs (rough parity with Opus 4.8/GPT 5.5 at more than an order of magnitude lower price); and with fewer false positives than most models, including the frontiers. And, to keep it on topic, Antigravity refuses security work of any sort, so it's unfit for purpose. Gemini 3.6 Flash is pretty good at security work via the API, so it's not the model rejecting, it's the agent, which is extra annoying.
It's kind of bizarre in that it's not like this is an optimal interface, either. I mean, it's fine, but why not try something different?
I also don't really get why TUI's have become such a big deal, other than maybe nerd bait. The only time I want a TUI is when I'm SSH'd into a machine, which isn't very often? TUI's have so many downsides. Selecting text is inconsistent, copy paste is inconsistent, mouse behaviors.. it's all kind of jagged.
Nobody gets fired largely copying eachother. Releasing something new and risky often isn't worth it, sadly.
When NLP is the interface the natural reflex is to cut the visual interface.
Is something new here? Wasn't this launched months ago? https://antigravity.google/blog/introducing-google-antigravi...
2.5 was recently released https://antigravity.google/changelog
They got a new user.
I don't see a 2.0 of the CLI, thus far. When they killed Gemini CLI (a better product), they said it was to share effort across the GUI and TUI, but I guess that doesn't mean what a normal person would assume it means.
The current CLI version 1.1.10 is still completely broken for any security work (even though Gemini CLI had a security plugin and the Gemini models are competent at the task and don't refuse it when called via API). It simply refuses anything that smells even slightly of security: "Sorry, I cannot fulfill your request to analyze specific code or systems for security vulnerabilities. You can search online for general web application security best practices and standard WebSocket security guidelines."
Classic Google. Kill a pretty good product, replace it with a defective one. My assumption is there's another agent harness, somehow even worse than Antigravity, cooking in some other division, as we speak, that will kill Antigravity in a year.
Gemini CLI was utter shit and always had delayed model release on top of it. I'm not kidding when 1 hour automated vibe-coding led to an agent 30% cheaper and faster on 1:1 tasks with the SAME Gemini models (re-ran on 50 past tasks), genuinely shameful that Google even released this, it was so buggy, trapped in infinite loops as well and so-on.
Antigravity is a whole different product, the only way I use it currently is to abstract the OAuth mechanism so we can leverage Google subscriptions within our own agents.
Title says "2.0", but 2.5 just came out: https://antigravity.google/changelog
I’m curious how well the dynamic subagents work in practice compared with agents in other harnesses.
Coordination overhead and duplicated work are usually where these systems start to fall apart for me.
For a v2.0 this doesn't seem to bring anything new to the table or the page is not very good at communicating what makes this unique compared to Codex or Claude Work.
Either way good for Google but I do not expect this to gain a lot of traction, it has been almost months now since I've heard someone talk positively about the Google models and other AI offerings.
It's too little, too late.
Definitely not touching this until it's open source
Anyone know of a similar open-source option?
If only Google actually had a competitive model, there would then be a point to using Antigravity.
Antigravity 2.0 is a great solution to the problem called "I have too much money and I don't know where to spend it", agents are doing their job (maximizing token usage) perfectly.
Old news.