Google has fundamentally reimagined how developers build software, moving away from traditional integrated development environments (IDEs) toward a multi-agent orchestration model. At its I/O 2026 developer conference, the company unveiled Antigravity 2.0, a standalone desktop application designed entirely around agent-driven workflows rather than code editing. This shift reflects a broader recognition that modern development increasingly requires multiple AI agents working in parallel to solve complex problems, rather than a single tool responding to individual prompts.

What Is Antigravity 2.0, and How Does It Differ From the Original?

Antigravity 2.0 is not an update to Google's existing IDE; it is a completely separate product built from the ground up as an agent orchestration platform. The new desktop application allows developers to coordinate multiple agents executing tasks in parallel, define scheduled background tasks that invoke agents automatically, and manage dynamic subagents for complex workflows. Unlike traditional IDEs that focus on code editing and syntax highlighting, Antigravity 2.0 treats agents as the primary abstraction, converting what was once a single-turn tool into something closer to a persistent automation pipeline.

One particularly practical addition is scheduled task automation. Rather than manually prompting an agent each time a task needs to be completed, developers can now define tasks that invoke agents automatically in the background. Google also added native voice command support, allowing developers to interact with agents through spoken instructions, consistent with similar additions to consumer products like Gmail and Docs.

How Is Google Expanding Antigravity Beyond the Desktop?

Google is not limiting Antigravity to a single interface. Instead, the company is releasing four complementary surfaces that together form a unified developer ecosystem:

• Antigravity CLI: A command-line interface built in Go for developers who prefer terminal-based workflows, offering faster execution and asynchronous task orchestration without a graphical interface.
• Antigravity SDK: A programmatic interface that lets developers define custom agent behaviors and host them on their own infrastructure, useful for teams embedding Antigravity-style agents into internal tools or products.
• Gemini Enterprise Agent Platform: An enterprise-facing deployment path that allows Google Cloud customers to connect Antigravity directly to their existing cloud projects and infrastructure.
• Managed Agents in the Gemini API: Infrastructure-level isolation for agent execution, allowing developers to spin up a full isolated Linux environment with a single API call, complete with persistent state across multi-turn sessions.

Critically, all four surfaces share the same underlying agent harness, meaning improvements to core agents are automatically applied everywhere developers use them. This unified architecture eliminates the fragmentation that plagued earlier developer tools.

What Happened to Gemini CLI, and Why the Transition?

Google is retiring Gemini CLI, the terminal tool it shipped in 2025, in favor of Antigravity CLI. The decision reflects a fundamental shift in how developers actually work. When Gemini CLI launched, it proved that the terminal could be an excellent interface for AI-assisted tasks. However, user feedback revealed that workflows had outgrown single-agent interactions; developers now require multiple agents communicating with each other to split work and solve complex problems.

"Your workflows have simply outgrown those early days of 2025. Gemini CLI proved the terminal could be an incredible interface for agentic tasks, but your needs shifted. You now require multiple agents communicating with each other to split up the work and solve complex problems," stated Dmitry Lyalin, Group Product Manager at Google.

Dmitry Lyalin, Group Product Manager at Google

On June 18, 2026, Gemini CLI and Gemini Code Assist IDE extensions will stop serving requests for Google AI Pro and Ultra users, as well as free users. However, organizations using Gemini CLI or IDE extensions through Gemini Code Assist Standard or Enterprise licenses will retain access and continue receiving updates. Antigravity CLI preserves the most critical Gemini CLI features, including Agent Skills, Hooks, Subagents, and Extensions, now rebranded as Antigravity plugins.

What Powers Antigravity, and How Fast Is It?

Underpinning the entire Antigravity ecosystem is Gemini 3.5 Flash, Google's latest language model, which is set as the default across all Antigravity surfaces. According to Google, Gemini 3.5 Flash outperforms Gemini 3.1 Pro across nearly all benchmarks while running four times faster than other frontier models. This speed advantage is practically significant when multiple agents run in parallel, since model latency compounds across concurrent agent calls. Antigravity CLI, built in Go, is also notably snappier and more responsive than its predecessor.

How Can Developers Get Started With Antigravity?

Google is expanding where developers can begin and continue their work. A new Google AI Studio mobile app is available for pre-registration, allowing developers to capture ideas on the go and have a working prototype ready when they return to their desktop. An Export to Antigravity integration lets entire projects move from AI Studio to local Antigravity development with a single click, including all project context.

Google is also introducing new integrations and capabilities:

• Workspace Integration: Agents can now natively call Google Workspace APIs and embed them directly into applications, useful for workflows that need to interact with Google Docs, Sheets, Calendar, or other Workspace services programmatically.
• Android Support: Developers can build Android apps with just a prompt, and Google Play Console support is now available directly in Google AI Studio, enabling app publishing to the test track without leaving the Studio environment.
• Pricing Tier: Google is introducing a new $100 per month AI Ultra plan offering five times higher usage limits in Antigravity compared to the existing Google AI Pro plan.

Antigravity CLI is available to everyone starting immediately, and developers can access technical documentation and video walkthroughs to ease the transition from Gemini CLI. For those using Google Cloud projects, Antigravity CLI is accessible now with Google Cloud API keys.

Why Does This Matter for the Future of Developer Tools?

Google's shift from IDE-centric assistance to multi-agent orchestration signals a broader industry recognition that AI-assisted development is fundamentally changing. Rather than treating AI as a code-completion feature bolted onto an existing editor, Google is redesigning the entire developer experience around agent coordination. This move suggests that the future of development tools will prioritize workflow automation, parallel task execution, and persistent background agents over traditional code-editing paradigms. For developers accustomed to IDEs, the transition may feel unfamiliar, but Google's unified architecture across CLI, SDK, desktop, and API surfaces aims to make the shift as seamless as possible.