Experience liftoff with the next-generation IDE
Google Antigravity's Editor view offers tab autocompletion, natural language code commands, and a configurable, context-aware agent.
Built on Google's latest breakthrough: Gemini 3 — the most intelligent model driving agentic coding capabilities
Advanced AI-powered autocompletion that understands your codebase context and predicts your next move with unprecedented accuracy.
A more intuitive task-based approach to monitoring agent activity, presenting you with essential artifacts and verification results to build trust.
Intuitively integrate feedback across surfaces and artifacts to guide and refine the agent's work in real-time.
Synchronized agentic control across your editor, terminal, and browser for powerful development workflows.
Manage multiple agents at the same time, across any workspace, from one central mission control view.
Advanced AI-powered autocompletion that understands your codebase context.
A more intuitive task-based approach to monitoring agent activity.
Intuitively integrate feedback across surfaces and artifacts.
Synchronized agentic control across your editor, terminal, and browser.
Manage multiple agents at the same time from one central view.
for the agent-first era
Google Antigravity is built for user trust, whether you're a professional developer working in a large enterprise codebase, a hobbyist vibe-coding in their spare time, or anyone in between.
Streamline UX development by leveraging browser-in-the-loop agents to automate repetitive tasks.
Build production-ready applications with confidence with thoroughly designed artifacts and comprehensive verification tests.
Streamline operations and reduce context switching by orchestrating agents across workspaces using the Agent Manager.
Every advancement in model intelligence for coding has encouraged us to rethink how development should be done. The Integrated Development Environment (IDE) of today is a far cry from the IDE of just a few years ago. Gemini 3, our most intelligent model, represents a step-change for agentic coding, and requires us to think about what the next step-change of an IDE should be.
Today, we are introducing Google Antigravity, our new agentic development platform. Powered by Gemini 3, Google's latest and most advanced AI model, Antigravity delivers a familiar AI-powered IDE experience while evolving towards an agent-first future. With browser control capabilities, asynchronous interaction patterns, and an agent-first product form factor, Gemini 3 enables agents to autonomously plan and execute complex, end-to-end software tasks.
Our first product that brings four key tenets of collaborative development together
Antigravity provides context on agentic work at a more natural task-level abstraction, with the necessary and sufficient set of artifacts and verification results, for the user to gain trust.
Agents can operate across all surfaces simultaneously and autonomously, with a form factor that exposes this autonomy optimally and allows users to interact asynchronously.
Intuitive async user feedback across every surface and Artifact, whether it be Google-doc-style comments on text Artifacts or select-and-comment feedback on screenshots.
Antigravity treats learning as a core primitive, with agent actions both retrieving from and contributing to a knowledge base for continuous improvement.
View the Agent's task list, review the implementation plan post-research and pre-implementation, or scan the walkthrough at completion.
Autonomously, an Antigravity Agent writes code for a new frontend feature, uses the terminal to launch localhost, and actuates the browser to test that the new feature works.
User spawned an Agent to do background research in a different workspace while focusing on a more involved task in the foreground, using the Inbox and side panel in the Agent Manager to be notified of progress.
An example of feedback on textual Artifacts such as an implementation plan and an example of feedback on a visual Artifact such as a screenshot taken by the Agent.
Agent learning from work and feedback to generate and leverage knowledge items, viewable from the Agent Manager.
Comprehensive tools for the modern developer
Able to autonomously operate across your editor, terminal, and browser.
Deliverables from the Agent to communicate its progress with you.
Fully-featured AI-powered IDE with Tab, Command, Agents, and more.
Your mission control to manage multiple agents in parallel, across multiple workspaces.
Leave comments and feedback on any Artifact to better guide the Agent.
Manage higher-level tasks for the Agent, not individual tool calls.
Antigravity learns from conversations to populate a reusable knowledge base.
See what builders and developers like you have been able to achieve with Google Antigravity
We challenged robotics researchers to build an auto-playing pinball machine with Google Antigravity.
We iterated on the design of a flight tracker app using Nano Banana within Google Antigravity.
We challenged robotics researchers to build an inverted pendulum controller with Google Antigravity.
We rapidly added a number of features to a collaborative whiteboard app by orchestrating multiple parallel agents in Google Antigravity.
Everything you need to know about Google Antigravity IDE
A: Yes! Google Antigravity is 100% free during the public preview with generous rate limits on Gemini 3 Pro usage. You can use all features at no cost.
A: Antigravity is the only AI IDE with: (1) Built-in browser automation, (2) Multi-agent orchestration via Agent Manager, (3) Powered by Google's latest Gemini 3 model, and (4) Completely free. See our detailed comparison table.
A: Antigravity supports three powerful models: Gemini 3 Pro (Google's latest), Claude Sonnet 4.5 (Anthropic), and GPT-OSS (OpenAI's open-source models). You can switch between them based on your needs.
A: Mac: macOS 12+ (Monterey or later). Windows: Windows 10 64-bit or later. Linux: glibc >= 2.28, glibcxx >= 3.4.25 (Ubuntu 20+, Debian 10+, Fedora 36+, RHEL 8+).
A: Yes! Antigravity is built on VS Code, so you can easily import your settings, extensions, and keybindings from VS Code or Cursor. Your familiar development environment carries over seamlessly.
A: The Agent Manager is a unique feature that lets you run multiple AI agents simultaneously across different workspaces. For example, one agent can research APIs while another builds your frontend - all managed from a single dashboard. No other AI IDE has this capability.
A: Antigravity includes an integrated Chrome browser that agents can control directly. After writing code, agents can automatically launch your app, interact with it in the browser, take screenshots, and verify functionality - all without leaving the IDE.
A: Yes. Google Antigravity follows Google's privacy and security standards. Your code is processed to provide AI assistance but is not used to train models. Review the Privacy Policy for complete details.
A: Antigravity supports all major programming languages including JavaScript/TypeScript, Python, Java, C++, Go, Rust, PHP, Ruby, and more. If VS Code supports it, Antigravity supports it.
A: Google provides "generous rate limits" that refresh every 5 hours. Most developers will never hit these limits during normal use. If you do, you'll get clear notifications and can continue after the refresh period.
Google Antigravity for individuals at no charge
Experience liftoff in 3… 2… 1…
Download Now - Free