Google Antigravity 2.0: From Code Editor to Autonomous AI Agent Orchestrator

Google today announced a dramatic expansion of its Antigravity platform at I/O 2026, repositioning it from a coding environment into a full-scale development and management platform for teams of autonomous AI agents. The move comes six months after Antigravity’s initial launch and introduces a standalone desktop application, a command-line interface, an SDK, and deep integration with Google Cloud for enterprise customers.

“We are expanding Antigravity beyond a coding environment and turning it into a platform to develop and manage teams of autonomous AI agents,” said Koray Kavukcuoglu, CTO of Google DeepMind and Chief AI Architect at Google, during a press briefing ahead of the event. The company claims millions of developers are already building with the platform.

Antigravity 2.0: A Central Hub for Agent Orchestration

The centerpiece of the announcement is Antigravity 2.0, a new standalone desktop application that acts as a central hub for coordinating multiple agents simultaneously. Developers can now have one agent generating code, another producing brand assets, and a third handling product architecture planning—all running in parallel.

Google Antigravity 2.0: From Code Editor to Autonomous AI Agent Orchestrator — Source: thenewstack.io

“Google Antigravity is our agent-first development platform for developers to take an idea and turn it into a production-ready app,” wrote Varun Mohan, Director of Software Engineering at Google DeepMind, and Logan Kilpatrick, Member of the Technical Staff, in a blog post. “Today, we’re expanding the Antigravity ecosystem to manage and deploy agents that can integrate across key developer surfaces.”

New CLI for Terminal-First Developers

For developers who prefer the command line, Google is introducing the Antigravity CLI, a lightweight interface for spinning up agents without a graphical environment. Existing Gemini CLI users are being encouraged to migrate to this new tool.

SDK Co-Optimized for Gemini 3.5 Flash

Rounding out the product expansion is the Antigravity SDK, providing programmatic access to the same agent harness powering Google’s internal products. The SDK is co-optimized for Gemini 3.5 Flash, which Google says was developed alongside Antigravity 2.0 as the platform’s primary workhorse model. The company claims it outperforms Gemini 3.1 Pro on nearly all benchmarks and runs four times faster than competing frontier models.

In the cloud, Managed Agents in the Gemini API allow a single API call to spin up a full agent that reasons, uses tools, and executes code inside a persistent, isolated Linux environment. State and files persist across follow-up calls, enabling multi-turn sessions without re-initialization.

Enterprise Integration and Pricing

The enterprise angle is addressed through integration with the Gemini Enterprise Agent Platform, letting Google Cloud customers connect directly to their Cloud projects. A new $100-per-month Google AI Ultra tier is also being introduced for high-volume deployments.

Background

Antigravity originally launched six months ago as a coding environment aimed at helping developers write and debug code faster. However, Google has now pivoted to position it as an agent-first platform. The shift reflects the broader industry trend toward autonomous AI agents that can perform complex, multi-step tasks across different domains.

What This Means

This expansion signals that Google is betting heavily on autonomous agents as the next major developer platform. By providing a unified suite of tools—desktop app, CLI, SDK, and cloud managed agents—Google aims to lower the barriers for building production-ready multi-agent systems. For enterprises, the cloud integration and $100 Ultra tier make it easier to deploy agents at scale. Developers can expect a more integrated workflow where agents collaborate in real time, potentially accelerating everything from software development to marketing campaigns.

The announcement also positions Antigravity as a direct competitor to emerging agent platforms from Microsoft, OpenAI, and other tech giants. With Gemini 3.5 Flash as the backbone, Google claims superior performance and speed, which could sway developers looking for efficient agent orchestration.