Google has fundamentally reorganized how developers build software by moving from IDE-centric assistance to multi-agent workflow management as the primary abstraction. At its I/O 2026 developer conference, the company unveiled Antigravity 2.0, a standalone desktop application designed entirely around agent orchestration, alongside a command-line interface (CLI), software development kit (SDK), managed execution options, and enterprise support.

What Is Antigravity 2.0 and Why Does It Matter?

Antigravity 2.0 represents a significant departure from traditional development environments. Rather than treating AI as a helper within an existing IDE, Google built this platform from the ground up to orchestrate multiple specialized agents working in parallel on complex tasks. The desktop application lets developers spin up dynamic subagents to handle different parts of a workflow simultaneously, schedule background automation tasks, and integrate with Google's ecosystem of tools including AI Studio, Android, and Firebase.

The shift is practically significant because it converts AI from a single-turn tool into something closer to a persistent automation pipeline. Developers can now define tasks that invoke agents automatically in the background rather than manually prompting an agent each time they need help. Google also added native voice command support to Antigravity, consistent with similar additions to consumer products like Gmail and Docs.

How Can Developers Access and Deploy Antigravity?

Google is releasing four complementary surfaces that together form a unified developer harness, each designed for different workflows and deployment scenarios:

• Antigravity CLI: A lightweight, terminal-based interface for developers who prefer command-line workflows. It shares the same agent harness as the desktop application, meaning all future improvements automatically apply across both surfaces. The CLI fully replaces the Gemini CLI and preserves critical features including Agent Skills, Hooks, Subagents, and Extensions.
• Antigravity SDK: Provides programmatic access to the same agent harness powering Google's own products. Optimized for Gemini models, it lets developers define custom agent behaviors and host them on their own infrastructure, relevant for teams that want to embed Antigravity-style agents inside their own products or internal tooling.
• Managed Agents in the Gemini API: Removes the friction of infrastructure setup by delivering the power of the Antigravity agent harness via a single API call. Each interaction creates an isolated Linux environment that can be resumed in follow-up calls with all files and state intact, enabling seamless multi-turn sessions without reinitializing context.
• 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.

Underpinning the entire ecosystem is Gemini 3.5 Flash, which Google is setting as the default model across Antigravity. According to Google's team, 3.5 Flash outperforms Gemini 3.1 Pro across almost all benchmarks while running four times faster than other frontier models. The speed advantage is practically significant when multiple agents are running in parallel, since model latency compounds across concurrent agent calls.

What New Developer Tools Are Available for Android and Web Development?

Google substantially expanded where developers can start and continue their work. A new Google AI Studio mobile app is available to pre-register, letting developers capture ideas on the go and have a working prototype ready when they return to their desktop. Through a new Export to Antigravity integration, entire projects can be moved from AI Studio to local Antigravity development with a single click, including all project context.

For Android development specifically, Google introduced a stable Android CLI that enables AI agents to tap directly into the power of Android Studio. The CLI can handle tasks like downloading the Android SDK and running apps on Android devices, allowing developers to create high-quality Android apps using any agent, language model, and tool of their choice. Google also open-sourced Android skills to help language models execute best practices for complex workflows and APIs, such as migrating to Jetpack Compose or Jetpack Navigation 3 migration.

A particularly notable feature is the migration agent, a new Android Studio capability that can migrate app code to native Kotlin Android apps regardless of whether the source is React Native, a web framework, or iOS. The agent analyzes code and handles the heavy lifting, turning migrations that would have taken weeks into just hours.

For web development, Google introduced WebMCP, a proposed open web standard that allows developers to expose structured tools like JavaScript functions and HTML forms so browser-based AI agents can execute complex tasks with greater speed, reliability, and precision. The experimental WebMCP origin trial starts in Chrome 149, with support for Gemini in Chrome coming soon. Google also launched Modern Web Guidance, which helps developers build more performant, accessible, and secure web experiences by providing coding agents with a set of expert-vetted skills supporting over 100 use cases.

What Pricing and Availability Options Are Available?

Google introduced a new $100 per month AI Ultra plan offering 5 times higher usage limits in Antigravity compared to the existing Google AI Pro plan. This tiered pricing structure allows developers to choose the level of agent orchestration and parallel execution capacity that matches their project needs.

The company is also bringing Chrome DevTools' capabilities to AI agents with Chrome DevTools for agents, helping developers scale their workflow with verifying, debugging, and optimizing code in real time. Agents can automate quality audits, emulate real-world user experiences, hand over sessions with auto-connect, and more without manual oversight.

How Does This Compare to Microsoft's Competing Approach?

While Google focuses on agent orchestration as the primary abstraction, Microsoft is taking a complementary approach with its Foundry platform. Microsoft's May 2026 update to Foundry includes trace-based evaluation for external and hosted agents, allowing developers to grade real production traces from Foundry, Google Cloud Platform (GCP), Amazon Web Services (AWS), or any framework without hand-curated datasets. Microsoft also expanded its model catalog to include xAI's Grok 4.3 for advanced agentic workloads and DeepSeek V4 for open-model choice.

Microsoft's Foundry Agent Service now includes preview skills and toolboxes through the azure-ai-projects SDK version 2.2.0, which ships across Python, JavaScript/TypeScript, and.NET with external agent definitions, skills, toolboxes, model weight registry, routines, and optimization jobs. This represents a different architectural philosophy where agents are integrated into a broader platform for model selection, evaluation, and governance rather than being the primary abstraction.

Both platforms reflect a broader industry shift toward agent-first development, but they differ in emphasis. Google's Antigravity prioritizes orchestration and parallel execution as the core developer experience, while Microsoft's Foundry emphasizes governance, evaluation, and cross-framework compatibility. Developers choosing between them should consider whether they prioritize rapid agent orchestration and Google ecosystem integration or broader model choice and enterprise governance controls.