Cursor and Google Antigravity, fact by fact
| Fact | Cursor | Google Antigravity |
|---|---|---|
| Stars | 33,265Verified 8 Oct 2026 | not tracked for Google Antigravity |
| Newest commit | 12 May 2026148 days old when we read itVerified 8 Oct 2026 | not tracked for Google Antigravity |
| Contributors | 31Verified 8 Oct 2026 | not tracked for Google Antigravity |
| Homebrew installs | 3,588 in 30 dayscursorVerified 8 Oct 2026 | not tracked for Google Antigravity |
| Repository | cursor/cursorVerified 8 Oct 2026 | not tracked for Google Antigravity |
What we know about Google Antigravity
Google Antigravity is a platform rather than an editor: its IDE extensions put the same agent — side-panel chat, inline diff review and interactive plans — inside the editor you already use, so adopting Antigravity does not require adopting its IDE.
“Antigravity IDE Extensions bring Google’s agentic development platform directly into your favorite editor. Without switching your development environment, you can converse with agents in dedicated side panels, review granular inline diffs, inspect interactive plans, and execute multi-step enginee…”
Run Antigravity without leaving Visual Studio Code: Google's own extension puts agent chat, inline diff review and interactive plans into VS Code side panels, and installs a local `agy` backend service the first time you launch it.
“The Antigravity for Visual Studio Code extension brings the full agentic capabilities of Google Antigravity into VS Code. Converse with agents in dedicated side panels, review granular inline diffs, inspect interactive plans, and execute multi-step engineering tasks without leaving your editor.”
Start a long refactor at the desk and steer it from a phone: Remote Control drives the Antigravity 2.0 session running on your own machine from any web browser.
“Antigravity Remote Control allows you to securely connect to and drive your Antigravity 2.0 desktop sessions running across your machines from any web browser.”
Put Gemini, Claude and an open-weights model on the same task without paying three vendors: the $0 tier lists Claude Sonnet & Opus 4.6 and gpt-oss-120b beside Gemini 3.1 Pro.
“Agent model: access to Gemini 3.5 Flash, Gemini 3.1 Pro, Gemini 3 Flash, Claude Sonnet & Opus 4.6, gpt-oss-120b”
You cannot point Antigravity at a model key you already hold: the plans page states there is no bring-your-own-key or bring-your-own-endpoint path, so the quota Google grants you is your only supply.
“There is currently no support for: · Bring-your-own-key or bring-your-own-endpoint for additional rate limits · Organizational tiers via contract”
The Antigravity sign-in works in Antigravity alone: reaching it from Claude Code, OpenCode or any other third-party client breaks the Terms of Service and can end the account.
“Using third party software, tools, or services to access Antigravity is a violation of our Terms of Service, and severely degrades the experience for legitimate product users. Such actions may be grounds for suspension or termination of your account.”
The CLI runs agent shell commands on the bare machine until you switch the sandbox on yourself, because `enableTerminalSandbox` ships set to false.
“enableTerminalSandbox (boolean, default: false): Restricts all local execution commands launched by agents to OS containment rings.”
An enterprise should not standardise on the Antigravity IDE: Gemini Enterprise supports Antigravity 2.0, the CLI and the IDE extensions, of which Visual Studio Code is the first, and excludes the standalone IDE.
“Enterprise integration is supported for Antigravity 2.0, Antigravity CLI, and Antigravity IDE Extensions. Antigravity IDE (standalone) is currently not supported for enterprise deployments.”
What Google Antigravity costs
Antigravity costs $0 a month for an individual, and the pricing page now labels that tier Generally Available rather than a preview.
“Generally Available For Individuals · $0/month · Experience Antigravity without a subscription plan”
Google publishes no request count for that $0 tier, and says why: the limit is set by spare capacity and tracks how much work the agent does, so a simple task buys more prompts than a hard one.
“The baseline rate limits are primarily determined to the degree we have capacity, and exist to prevent abuse. Under the hood, the rate limits are correlated with the amount of work done by the agent, which can differ from prompt to prompt. Thus, you may get many more prompts if your tasks are mor…”
Going over the free quota is not possible: only Google AI Pro and Ultra subscribers can spend purchased AI credits, billed at Gemini Enterprise Agent Platform consumption rates.
“Users on Google AI Pro or Ultra plans can utilize purchased AI credits (or any one-time promotional credits) for additional overage usage above the baseline provided quota. AI credits are consumed at standard Gemini Enterprise Agent Platform consumption pricing.”
What this page does not answer
We have researched Google Antigravity and we have not researched Cursor. That means the judgments above answer for one tool and not for the other, and we publish no price for Cursor because we have not read its pricing page. Nothing on this page about Cursor is our opinion; there is not enough evidence yet for one.
Questions people ask
- Are Cursor and Google Antigravity still maintained?
- Cursor has taken no commit on cursor/cursor (main) for 148 days; the newest is 12 May 2026. Google Antigravity has no repository we track. Both readings come from the default branch of each repository, on the date shown beside them.
- What does Google Antigravity cost?
- Cursor: we have not read its pricing page, so we publish no price for it. Google Antigravity: Antigravity costs $0 a month for an individual, and the pricing page now labels that tier Generally Available rather than a preview. Google publishes no request count for that $0 tier, and says why: the limit is set by spare capacity and tracks how much work the agent does, so a simple task buys more prompts than a hard one. Going over the free quota is not possible: only Google AI Pro and Ultra subscribers can spend purchased AI credits, billed at Gemini Enterprise Agent Platform consumption rates. Every figure here is quoted from the vendor's own page and linked beside the claim.
How we check this page
- Machine facts. Stars, contributors, the newest commit on the default branch, the licence GitHub reports and the latest stable release come from the GitHub API, and download counts from npm, PyPI, Homebrew and the VS Code Marketplace. Each value carries the day it was last confirmed, never the day this page was built. The line under each label is arithmetic on those two values.
- Judgments. Every claim about what a tool suits, what it is bad at and what it costs is quoted from a page we read, and that page is linked beside the claim. Where there is no link, we wrote no claim.
- Index status. Google Antigravity carries claims we read, quoted and linked; Cursor does not. So this page is offered to search engines.
Related comparisons
Pairs we can answer for come first.