Antigravity IDE Guide

Independent reference. Not affiliated with, endorsed by or sponsored by Google LLC.

Checked 30 August 2026

0 models in the picker
0 surfaces, not one app
0 operating systems

Every figure on this site is taken from Google's own pages and carries the date it was read. Nothing here is a benchmark we ran.

Google Antigravity, written down and dated.

An independent reference to the agent-first development platform Google launched in November 2025 — what the surfaces actually are, which models you can pick, what the quotas cost, and where the published numbers stop.

Nothing hosted here No account No cookies Google's own site, antigravity.google
Model benchPick one

Gemini 3.7 Flash

Select a model to read its published profile.

Intelligence
Speed
Latency
Provider
Quota pool
In picker
Per 1M in / out

Bars render Google's own three-step words — Low, Medium, High, Fast — from the models table, not measurements taken by anyone here. A blank bar means Google publishes no rating for that model. Source: antigravity.google/docs/models, read 30 August 2026.

Directory

Four rails, grouped the way Google's own documentation groups them. Names are Google's; the one-line descriptions are ours.

Source: antigravity.google/docs and antigravity.google, read 30 August 2026.

A — first rail

Antigravity is not one program, and that is the part most write-ups get wrong.

At launch there were two views: an editor and a manager. By August 2026 the product page lists five separate surfaces onto the same agents. Which one you use changes almost nothing about what the agent can do and almost everything about how you watch it work.

A

Surfaces — Five ways in, not one application

5 entries

Antigravity IDE

The full agentic editor: tab autocompletion, natural-language commands and an agent that operates across the editor, terminal and browser.

Antigravity 2.0

Google's phrase for it is a command centre — managing several local agents running in parallel rather than one conversation at a time.

Antigravity CLI

A terminal-first surface for the same agents, for people who would rather not leave the shell.

Antigravity SDK

A Python kit for prototyping custom agents against the platform.

Antigravity Extensions

Extension support, so an existing editor set-up carries over.

B

Artifacts — What the agent hands back instead of a log

5 entries

Implementation plans

The agent writes the plan before it writes the code, so the thing you review is the intent rather than the diff.

Task lists

Work broken into steps you can follow while it runs.

Screenshots

Visual evidence that the change did what it said, captured by the agent.

Browser recordings

A replay of the agent driving the browser — the strongest form of verification the platform produces.

Artifact review

Comments and feedback can be left on any artifact to steer the next pass.

C

Customisation — What you can bolt on

6 entries

MCP servers

Model Context Protocol connections to tools and data outside the editor.

Skills

Packaged procedures the agent can call for a particular kind of task.

Rules

Standing instructions that apply to a project without being retyped.

Plugins

Bundles that install a set of the above together.

Hooks

Points where your own code runs in response to what the agent does.

Sidecars

Companion processes running alongside the agent.

D

Agent capabilities — How far it is allowed to go

6 entries

Slash commands

Named shortcuts for specialised tasks, typed into the same chat input.

Teamwork

Several agents working the same repository without treading on each other.

Permissions

The controls that decide what the agent may do unattended.

Subagents

An agent delegating part of a task to another agent.

Worktree mode

Starting a run in a fresh git worktree instead of your working copy — the difference between an experiment and an edit.

Remote control

Reaching a running agent from somewhere other than the machine it is on.

Index — models

0 you can choose
0 separate quota pools

Gemini models and third-party models draw down different allowances. The interface shows each as a five-hour figure and a weekly one.

Source: antigravity.google/docs/models, read 30 August 2026.

B — the picker

Seven reasoning models, two quota pools, one image tool.

The interesting detail is the pooling. Gemini usage and third-party usage are metered separately, so exhausting Claude does not stop you working — it stops you working that way. Google's plans page puts access to third-party models on the Ultra tier.

Google publishes speed, latency and intelligence words for its own models and not for the third-party ones. We have left those cells blank rather than filling them in.

Model
Published profile
Gemini 3.7 Flash Google
In the pickerGemini poolIntelligence: MediumLatency: Low$0.75 / $3.75 per 1M
Gemini 3.6 Flash Google
In the pickerGemini poolIntelligence: MediumLatency: Low
Gemini 3.5 Flash Google
In the pickerGemini poolIntelligence: MediumLatency: Low
Gemini 3.1 Pro Google
In the pickerGemini poolIntelligence: HighLatency: Low
Claude Sonnet 4.6 (thinking) Anthropic
In the pickerClaude / GPT pool
Claude Opus 4.6 (thinking) Anthropic
In the pickerClaude / GPT pool
GPT-OSS-120b OpenAI (open weights)
In the pickerClaude / GPT poolIntelligence: Medium
Nano Banana 2 Google
Called by the agentImage tool

Prices shown are the published per-million input / output token figures where Google states them. Gemini 3.7 Flash is on an introductory price through the end of 2026, rising to $1.50 / $7.50 on 1 January 2027. Source: Gemini 3.7 Flash in Google Antigravity, 13 Aug 2026.

C — the sequence

What a run actually looks like

Six steps, in the order Google's getting-started page puts them, with the thing each step is easy to get wrong noted underneath.

Source: antigravity.google/docs, read 30 August 2026.

01

The file comes from Google's domain

Builds for macOS, Windows and Linux live on antigravity.google. If the setup offers Replace, that is the expected prompt.

This site links to that page and mirrors nothing. Any other site handing you an Antigravity build is not Google.

02

Open a project

The folder icon with a plus, in the left sidebar. A project is a local folder or a git repository.

Nothing is uploaded by opening a project; the agent works against the files on your machine.

03

Say what you want, not which tool to run

The goal goes in the chat input in plain language. This is the whole premise: you are handing over a task, not a command.

Google's own framing is operating “at a higher, task-oriented level”.

04

Choose local or a new worktree

Local mode works in your checkout. New worktree mode branches into a fresh git worktree.

Worktree mode is the one to reach for when you are not yet sure the agent should be trusted with the change.

05

Read the artifacts, not the log

The agent produces a plan, a task list, screenshots and browser recordings. Comments left on any artifact steer the next pass.

This is the part that distinguishes it from autocomplete: the unit of review is the deliverable, not the token stream.

06

Watch the two limits

The interface shows a five-hour figure and a weekly one, tracked separately for Gemini and for Claude and GPT.

Google says limits are “correlated with the amount of work done by the agent, which can differ from prompt to prompt” — so they are not predictable from a prompt count.

Before / after

Google's published comparison of Gemini 3.7 Flash against 3.6 Flash, 13 August 2026. Upper bar is 3.6, lower bar is 3.7.

Each bar is drawn on that benchmark's own scale, so the three rows are not comparable with each other.

Source: Gemini 3.7 Flash in Google Antigravity, 13 Aug 2026.

D — the evidence

One model generation of difference, measured by the vendor.

These are Google's numbers for Google's model, which is the correct amount of scepticism to hold about them. They are still the only paired figures published, and they are specific enough to check.

The number worth sitting with is the second one. On FrontierCode both cuts fail more tasks than they finish. An agent platform is not a reason to stop reading the diff.

Benchmark3.6 Flash 3.7 Flash
DeepSWE v1.1 49.0% 65.3%

Google's headline figure for the release: resolving real software engineering issues end to end.

FrontierCode 1.1 (Main) 34.4% 43.6%

A harder coding set, where both cuts still fail the majority of tasks. Worth keeping in view before delegating anything unattended.

WebDev Arena 1588 Elo

Published for 3.7 Flash only, so there is no paired 3.6 figure to show. An Elo rating is relative to the field, not a percentage.

Where the facts come from

Everything on this site is checked against Google's own pages, and dated.

Antigravity changes quickly — models, quotas and prices have all moved since launch. Figures here carry the date they were checked. When they disagree with Google's documentation, Google's documentation is right and this page is stale; tell us and we will fix it.

Nothing is hosted here: we do not host software, mirror an installer, or ask for an account, licence key or payment. Downloads, sign-in and support all live on Google's own domain.

Contact

editor@antigravity-ide-guide.com

YOGA ON THE GO WITH GARY LLC
1013 Evergreen Isles Drive
Sun City Center, FL 33573-7196
United States
Responsible for content: Lavinie Dedominicis

Corrections are welcome and are acted on — say which page and which figure.

Never enter a Google password, payment card or API key on this site. We will never ask for one.

© 2026 Yoga on the Go with Gary LLC Reviewed 30 August 2026 Independent reference. Not affiliated with, endorsed by or sponsored by Google LLC. Google, Antigravity and Gemini are trademarks of Google LLC, used here descriptively for identification.