Reviews praise Google Antigravity for accelerating real work, with users highlighting autonomous skills that manage email, calendars, and project setup, plus clear implementation plans and walkthroughs. Minor knocks include early-stage UI quirks, brief trial limits, and occasional fallback to weaker models; polish and agent management could improve. From the makers of
, feedback emphasizes strong multi-agent orchestration and big-feature execution, especially when paired with top models and vision inputs. Many compare it favorably to Cursor, Claude Code, and Copilot.
For a very long time I had all these ideas that I couldn't act on. Antigravity has allowed me to just explore and create again, which is a wonderful feeling. The recent addition of skills has exploded my workflow productivity, it literally handles my inbox and calendar for me now. I've been a Google fanboy for a long time and I love what they're doing here.
What needs improvement
Still has some minor UI quirks and small bugs as expected with a new tool, but nothing that stops the workflow. I’m excited to see more built-in skills added.
vs Alternatives
I’ve used Cursor and Claude Code extensively, but they always felt like advanced autocomplete. I chose Antigravity because it bridges the gap between "writing code" and "getting things done." The autonomous skills, handling my real-world emails, calendar, and project setup, along with the deep planning it applies to project architecture, make it the only tool that actually feels like a teammate instead of just a text editor.
The agent workflow seemed like a meaningful improvement over Cursor. It was easy to follow the agent's code exploration and "though process". The review workflow made it feel very natural to iterate on the agent's proposed solution.
What needs improvement
The onboarding/trial felt weak somehow. I ran out of free-usage fairly quickly, and it fell over onto weaker models. I wasn't prompted to upgrade. For a new product, I'd expect to be able to trial it fully-featured, and then decide whether to upgrade.
There were some UI bugs, but nothing I couldn't live with for a new product.
The most important thing is going to be model accuracy. It's worth giving up on UX for better code generation.
In that sense, I actually stalled. Antigravity had momentum, but then stalled and failed over to weaker models. I had to get back to work, so I switched back to Cursor + Claude Code.
The agent workflow seemed like a meaningful improvement over Cursor. It was easy to follow the agent's code exploration and "though process". The review workflow made it feel very natural to iterate on the agent's proposed solution.
What needs improvement
The onboarding/trial felt weak somehow. I ran out of free-usage fairly quickly, and it fell over onto weaker models. I wasn't prompted to upgrade. For a new product, I'd expect to be able to trial it fully-featured, and then decide whether to upgrade.
There were some UI bugs, but nothing I couldn't live with for a new product.
The most important thing is going to be model accuracy. It's worth giving up on UX for better code generation.
In that sense, I actually stalled. Antigravity had momentum, but then stalled and failed over to weaker models. I had to get back to work, so I switched back to Cursor + Claude Code.
Ratings
Ease of use
Reliability
Value for money
Report
297 views
Framer — Launch websites with enterprise needs at startup speeds.
Launch websites with enterprise needs at startup speeds.
Promoted
I like this ide; it's rough around the edges, but I see a lot of potential.
One blocker for me is the low rate limits on the pro plan. DO these go up if you're on the ultra plan? I'm struggling to find info on this
Report
Been using it for a few days and I love it. Very generous with AI limits and context windows too. The kicker is that Claude is better than Gemini in this platform but that’s another story!
Wondering why they rushed this out without finishing pricing, better product images... really looks rushed as hell
Report
Wow. This is really cool. I love playing around with it and I quickly ran out of tokens. So much fun!
Report
At launch Anti-Gravity still feels a bit clunky and buggy for what it is, I see the potential in it with a few tweaks just to make it feel more smooth however and good enough for first day launch
Safe to say: Antigravity is taking the lead among AI IDEs right now. Very well done to unexpectedly impress the whole world!
But surely, I wait for response from Cursor and Antropic. his competition is going to make our lives so much better :)
Report
Incredible so far. I felt tempted to throw feature request after feature request at it to see when it lost the plot. It did, but later than Claude code has in the past. Gemini 3 rocks!
RiteKit Company Logo API
Wondering why they rushed this out without finishing pricing, better product images... really looks rushed as hell
At launch Anti-Gravity still feels a bit clunky and buggy for what it is, I see the potential in it with a few tweaks just to make it feel more smooth however and good enough for first day launch
MultiDrive
Safe to say: Antigravity is taking the lead among AI IDEs right now. Very well done to unexpectedly impress the whole world!
But surely, I wait for response from Cursor and Antropic. his competition is going to make our lives so much better :)