Reviewers say Google Antigravity is strongest when it explains its reasoning, helps plan implementations, and supports complex work without constant context switching. Users highlight practical gains on infra, APIs, and architecture, and some say its newer skills make it useful beyond coding, though the multi-agent workflow is not essential for everyone. The main complaints are still rough edges: UI quirks, minor bugs, weaker handling of large multi-file projects, and limited control over answer length. Founders of Socra and PromptURLs also praise its big-feature design and parallel agent workflow.
+10
Summarized with AI
Reviews
All Reviews
Most Informative
AppSignal — Get full visibility into app health, errors, and performance
Get full visibility into app health, errors, and performance
Promoted
Its amazing, the only problem is the rate limit, too less tokens, but still its a game changer in the long run as currently many people are trying it out so they gotta keep strict rate limits.
Cline X Cursor X Claude code all rolled into one solution and then some. Love the agent manager. The agent manager is going to open up some really interesting usecases like multiple long running tasks. Parallel execution and research etc etc. I find my self building the same solution in 3 different branches with different models all the time. But up until now it required 3 ide's open etc. And lots of branch managment and cloning. So having one place to manage al that is going to be gold. One early feedback would be that maybe not dissalow working on files where there is a .gitignore file. At least, allow it to be overriden. Definitly will be using Antigravity if prices are competative.
Surprisingly good! I still need some more time to play around, but so good.
Keen to see how well the tab support compares against Cursor.
For now the agent interaction and UX are really good. Much better than I expected from a Google product
Update: it’s a bit silly if you reach the credit limits you can’t pay or buy credits etc. but I suppose perhaps few people with hit these limits
We will have to wait for a few days for the hype to cool down so we can use it at the full capacity. Too many people are on it at the moment I believe. Seems like a game changer but let's see how it will operate autonomously with larger projects other than the basic apps. So far seems decent.
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.
Some UI quirks and minor bugs, but very powerful overall. I really like how it handles implementation plans and walkthroughs. I think it will be great a couple months from now.
What needs improvement
Mostly needs some bugfixes and UI polish. E.g. sometimes one of the panels obscures an Accept/Reject button, so it's hard to see the app is waiting for user input. And when allowing certain commands, I haven't been able to make this stick yet. There's an allowlist for commands in the settings, but this doesn't seem to work for me.
Cursor never quite resonated with me, but I need to give it another shot. Claude Code is great with Opus 4.5, but way too expensive. Antigravity is very close to Claude Code, and as a paid Google AI Pro subscriber I haven't bumped into any limits yet. I actually like Copilot quite a bit as well.
I tried AntiGravity and am very satisfied, as it allowed me to be highly productive and tackle complex tasks efficiently. I am also very grateful to the team for making this possible, and I’m excited for future updates and what’s to come. 😊
What needs improvement
I think the biggest potential for improvement probably lies in enhancing the Agents. I’m not currently using the Agent Manager (CTRL + E), because, to be honest, I usually handle one task at a time, as the tasks are very complex and need to be reviewed and understood by me.
Its amazing, the only problem is the rate limit, too less tokens, but still its a game changer in the long run as currently many people are trying it out so they gotta keep strict rate limits.
DiffSense
Cline X Cursor X Claude code all rolled into one solution and then some. Love the agent manager. The agent manager is going to open up some really interesting usecases like multiple long running tasks. Parallel execution and research etc etc. I find my self building the same solution in 3 different branches with different models all the time. But up until now it required 3 ide's open etc. And lots of branch managment and cloning. So having one place to manage al that is going to be gold. One early feedback would be that maybe not dissalow working on files where there is a .gitignore file. At least, allow it to be overriden. Definitly will be using Antigravity if prices are competative.
Remention
DiffSense
@ohansemmanuel I think the limit is 5h. Then it resets.
Oasi
Is this an official Google product?
Yomio
We will have to wait for a few days for the hype to cool down so we can use it at the full capacity. Too many people are on it at the moment I believe. Seems like a game changer but let's see how it will operate autonomously with larger projects other than the basic apps. So far seems decent.
what a launch! google is so back.