Google Unveils Antigravity 2.0 Agent-First Stack

Google Unveils Antigravity 2.0 Agent-First Stack

Google overhauled its developer tooling at I/O 2026 on May 19, transforming its Antigravity platform from a single IDE into a comprehensive agent-first development stack. The company announced Google Antigravity 2.0, a standalone desktop application built entirely around agent orchestration alongside an Antigravity CLI, an Antigravity SDK, Managed Agents in the Gemini API, and enterprise support through the Gemini Enterprise Agent Platform. The announcement, which coincides with the launch of Gemini 3.5 Flash, marks Google’s pivot from traditional IDE-centric assistance toward multi-agent workflow management as the primary development abstraction.

Gemini 3.5 Flash AI model with rocket launch, Google logo, and agent-first technology visualization beyond IDEs.

The Antigravity 2.0 Platform Expansion

Antigravity 2.0 is a standalone desktop application that delivers an agent-optimized experience, acting as a central home for agent interaction and allowing developers to orchestrate multiple agents to execute tasks in parallel. It also features dynamic subagents for parallelized workflows, scheduled tasks for background automation and ecosystem integrations across Google AI Studio, Android and Firebase.

The restructuring splits what was previously a single application into five distinct surfaces. The Antigravity CLI is focused at developers who prefer terminal-based workflows, delivering a lightweight, high-velocity surface for creating new agents without a graphical user interface. Critically, it shares the same agent harness as Antigravity 2.0, meaning all future improvements to core agents are automatically applied across both surfaces.

The Antigravity SDK provides programmatic access to the same agent harness that powers Google’s own products. The SDK allows developers to define custom agent behaviors and host them on their own infrastructure, targeting engineering teams that require self-hosted deployments.

Gemini CLI Discontinuation and Migration

The Antigravity CLI fully replaces the Gemini CLI. Google encouraged Gemini CLI users to migrate to Antigravity CLI. According to Google’s documentation, Antigravity CLI preserves the most critical Gemini CLI features: Agent Skills, Hooks, Subagents, and Extensions, the last of which are now rebranded as Antigravity plugins.

The transition proved controversial among developers. Google pushed an automatic update to Antigravity on Tuesday, May 19, and developers opened their computers to find terminals, file explorers, and editing tools gone. Google announced Antigravity 2.0 at I/O 2026 the same day, but the automatic rollout turned functional development environments into chat interfaces. Developer forums filled with complaints within hours of the update.

Managed Agents in the Gemini API

The Managed Agents feature in the Gemini API provides infrastructure-level isolation for agent execution. With a single API call, developers can spin up an agent that reasons, uses tools, and executes code in an isolated Linux environment. Managed Agents are powered by the Antigravity agent harness, built on Gemini 3.5 Flash, and available via the Interactions API and in Google AI Studio.

This infrastructure shift removes the need for developers to build their own sandboxed execution environments. Managed Agents in the Gemini API spins up a full isolated Linux environment with a single API call, with persistent state across multi-turn sessions.

Pricing and Enterprise Access

Google introduced new pricing tiers alongside the platform expansion. The company is introducing a new AI Ultra plan priced at $100, offering 5x higher AI limits in Antigravity than the Pro plan. Google is also reducing the price of its top AI Ultra plan from $250 to $200, which allows for 20x higher limits than the Pro plan.

Antigravity in the Gemini Enterprise Agent Platform addresses organizational use cases by simplifying enterprise workloads and allowing Google Cloud customers to connect Antigravity directly to Google Cloud projects. This is the enterprise-facing deployment path for teams that need to operate agents within their existing cloud infrastructure.

Agent-First Development Model

Google used its annual developer conference on May 19, 2026, to push its software-building tools toward a model where AI agents, not humans, do the orchestration. Google is moving its developer tooling away from IDE-centric assistance and toward multi-agent workflow management as the primary abstraction.

Gemini 3.5 Flash outperforms Gemini 3.1 Pro across almost all benchmarks while running four times faster than other frontier models, providing the high-speed engine needed for real-world agentic workflows. The new model serves as the underlying engine for the Antigravity 2.0 platform and its agent orchestration capabilities.

Key Facts

  • The announcements were published on May 19, 2026, the opening day of Google I/O 2026.
  • The original Antigravity launched in November 2025 as a free public preview on macOS, Windows, and Linux.
  • Google split Antigravity into three separate downloads. The automatic update installed Antigravity 2.0, which does AI agent work. Developers who want their code editor back need to download Antigravity IDE separately.
  • New subscribers get $100 in bonus credits through May 25, 2026.
  • Gemini 3 Pro and Gemini 3.5 Flash (default), plus Anthropic’s Claude Sonnet 4.5 and OpenAI’s GPT-OSS are supported on the platform.

Sources

Sources

  1. Google Launches Antigravity 2.0 at I/O 2026: A Standalone Agent-First Platform with CLI, SDK, Managed Execution, and Enterprise Support – MarkTechPost
  2. I/O 2026 developer highlights: Antigravity, Gemini API, AI Studio
  3. Why Google’s Antigravity 2.0 AI Update Has Developers Furious
  4. Google launches Antigravity 2.0 with an updated desktop app and CLI tool at IO 2026 | TechCrunch
  5. Gemini 3.5 and Antigravity 2.0 headline Google I/O 2026 reveal
  6. Google Antigravity 2.0: Agent-First Dev Platform Has Landed