Hayz Labs

Google Antigravity CLI

GoogleDeveloper toolReleased 19 MayOfficial site for Google Antigravity CLI no referral link

Google's free terminal coding agent, replacing Gemini CLI; turn off data use in settings if code privacy matters.

Our callFirst look: Worth tryingChecked 11 Oct
ScoreNot scored yetWhen an independent coding-agent benchmark publishes current results for Antigravity CLI by name.
CostFreeFree plan; paid plans add more
Better optionNothing we scored beats it for coding

Should you use it?

Pick it if

Anyone who wants to try a coding agent in the terminal at no cost, or who used Gemini CLI.

Best for: Anyone who wants to try a terminal coding agent for free, or who used Gemini CLI (Coding agents Top 20)

Skip it if

You want to know which model does the work; Claude Code names its default, Opus 5.5.

You give up: Pricing page doesn't name models or limits; some Gemini CLI features are missing

The short version

What this is
A terminal coding agent from Google, part of the Antigravity platform. It replaced Gemini CLI for personal Google accounts on 18 June 2026.
Why it matters
It is Google's default terminal agent and costs nothing to try, but no one outside Google has tested it yet.
  • Gemini CLI stopped serving Google AI Pro, Ultra and free individual users on 18 Jun 2026; this is the replacement s2.
  • Free for individuals with basic weekly limits; paid Google AI plans raise them s1.
  • Google uses your interactions to improve its products unless you opt out in settings s3.

Good at

  • Free for individuals, with unlimited Tab completions and Command requests and basic weekly agent limits s1.
  • Can run several agents in the background from the terminal s4.
  • Keeps Gemini CLI's Agent Skills, Hooks, Subagents and Extensions, now called plugins s2.

Weak at

  • No independent test of it yet, and the pricing page does not name its models or their limits s1.
  • Google said at launch it would not match every Gemini CLI feature right away s2.
  • Your interactions are used to improve Google's products unless you change the setting s3.

Our take

If you used Gemini CLI on a personal Google account, you have already been moved here: Gemini CLI stopped serving Google AI Pro, Ultra and free individual users on 18 June 2026 s2. Antigravity CLI is written in Go and shares its agent with the Antigravity 2.0 desktop app s2. Business customers on Gemini Code Assist Standard or Enterprise keep Gemini CLI s2.

The appeal is the price. Individuals pay nothing and get basic weekly agent limits, and Google AI Pro or Ultra raise them s1. The pricing page gives no numbers for those limits and does not say which models you get, so it is hard to compare with Copilot or Codex on paper. Google's terms say it uses your interactions to improve its products and machine learning, and that staff may review them; you can change that in settings s3. Do that before pointing it at private code.

Not scored yet

This is a First look: the call above comes from the maker's own pages, so there is no score yet. When an independent coding-agent benchmark publishes current results for Antigravity CLI by name.

CodingAgents

New to this? What the scores and labels mean
0 to 100
Our score for one job, like writing or coding, compared with everything else out today. 100 is the best available today. For AI models we build it from public data, such as Arena's blind votes and Epoch AI's independent tests; apps and tools are scored on our own checklist. The same tool can score differently for different jobs, and where two likely ranges overlap, we call it a tie.
Our verdict
Use it: a top choice for most people. Worth trying: good, and worth a go. Depends: good for some people or one kind of job. Wait: too early to tell, or not out for everyone yet. Skip: something else does the job better.
First look
Just released. We say what it is and whether to bother, and give it a score once public results exist.
No score yet
None of the public sources we use covers it yet, or the only evidence is from a source whose numbers we can't use, so we describe it in words instead.
Best buy
Nothing cheaper scores as well for that job.
Best free
The best score for that job that costs nothing, through a free plan or by running on your own computer.
Pay as you go
No monthly plan: you pay for each use, usually through a developer account.
Checked
The day we last confirmed the score and the price against the sources. Prices change often, so check the date.
AI model
The engine underneath, like GPT or Claude. You use it through an app or, if you code, directly.
Open source
Free to download and run on your own computer, so nothing leaves your machine.
How we score, in full

Alternatives

Better or cheaper for coding, from our scores, then the ones we'd also look at. The same kind of product comes first.

Compare side by side →

Evidence

Everything behind the call and the scores, folded so the page stays short. Spotted a wrong price, score or link? Report a mistake.

How we scored this

Reviews are drafted with help from AI models, including Anthropic's Claude. Model scores come only from outside leaderboards and independent evaluations, by a written rule.

No one paid for this review or gave us free access, and we earn nothing if you sign up. How we score

Sources 4
History 1 change

Every change to a rating, the price or our call, with the reason. Scores are against what exists on the day, so they drift down as better things ship. Older entries come from before we moved to scores.

  1. First look. No independent coding-agent result for it yet.
Use it well 3 guides on this site
esc
↑↓ move↵ openesc closeType a product, a job or a question

Keyboard shortcuts

CtrlK
search everything
/
search everything
gr
reviews: all AI, scored
gg
start here
gu
guides
gw
step-by-step workflows
gt
try-it tools
gs
setup
ga
about
[ ]
previous and next entry, or collection
t
theme: auto, light, dark
?
this sheet