Editorial illustration for Google Antigravity 2.0 Retains Gemini CLI Features as Antigravity Plugins
Google Antigravity 2.0 Retains Gemini CLI Features as...
Google Antigravity 2.0 doesn’t rebrand for the sake of rebranding. It keeps the CLI features developers actually use, Agent Skills, Hooks, Subagents, Extensions, and wraps them as Antigravity plugins. Here’s the critical shift: the CLI and the desktop app now share the exact same underlying agent harness.
Ship an enhancement to the core agent, and it lands on both surfaces. No trade-offs. No choosing one path and missing updates on the other.
The SDK unlocks programmatic access to that same harness, the one powering Google’s internal tools, letting you build custom agent behaviors and run them on your own infrastructure. For engineering teams that want Antigravity-style agents embedded in their products without leaning on Google Cloud, this is the lever. One API call spins up an agent that reasons, uses tools, and executes code in an isolated Linux sandbox.
Three elements make it work. For Google Cloud customers, the enterprise path wires Antigravity directly into existing projects, keeping agent workflows inside your cloud boundary with full access controls and audit trails. The entire Antigravity 2.0 ecosystem defaults to Gemini 3.5 Flash.
That’s the foundation. Now build on it.
The CLI keeps the Gemini CLI bits developers used, Agent Skills, Hooks, Subagents, and Extensions (but now they're renamed Antigravity plugins). The main thing to grasp is that the CLI and the desktop app run on the same underlying agent harness. So, any enhancements Google ships into the core agents, they land on both surfaces automatically.
You don't have to pick one and lose out on the ongoing updates to the other. With the SDK you get programmatic access to the same agent harness that powers Googles internal stuff, you know. It is designed for Gemini models, and it lets you shape custom agent behaviors, then run them wherever your own infrastructure lives.
Basically, this is the choice for engineering teams that want Antigravity-style agents embedded into their products, without having to rely on Googles cloud. This is the feature that, honestly, gets the most use with backend developers. With just one API call, you can spin up an agent that reasons and then uses tools, then it executes code in an isolated Linux place.
Three things make it work: If you are a customer of Google Cloud, the enterprise path allows you to connect Antigravity directly to your existing Google Cloud projects. This is important for teams needing agent workflows that are within their current cloud infrastructure, as well as having appropriate access controls and a complete audit trail. Whole Antigravity 2.0 eco system just defaults to Gemini 3.5 Flash.
The CLI isn’t just a nostalgic holdover. It’s the same engine the desktop app runs on, the same one Google’s internal teams use. That unity is the real unlock.
Developers get the full harness, Agent Skills, Hooks, Subagents, Extensions, now rebranded as plugins, without having to choose between command-line speed and a graphical interface. Updates cascade to both. No trade-offs.
The SDK takes it further. It hands you programmatic access to the same agent runtime that powers Google’s own workflows. Designed specifically for Gemini models, it lets you craft custom behaviors and deploy them anywhere your infrastructure lives.
No cloud lock-in. One API call spins up a reasoning agent, arms it with tools, executes code in an isolated Linux sandbox. That’s the kind of power backend engineers reach for daily.
Then there’s the enterprise path: a direct bridge into existing Google Cloud projects. For teams that need agent workflows inside their current infrastructure, with access controls and full audit trails. Antigravity 2.0 defaults to Gemini 3.5 Flash, but the framework is the point.
The pieces snap together. CLI and desktop, SDK and cloud. One harness, two surfaces, unbounded reach.
That’s the architecture that matters.
Common Questions Answered
What are the key features that Google Antigravity 2.0 retains from the previous version?
Google Antigravity 2.0 keeps all the CLI features developers rely on, including Agent Skills, Hooks, Subagents, and Extensions, which are now rebranded as Antigravity plugins. This ensures developers don't lose any existing functionality while benefiting from the new architecture and improvements.
How does the unified agent harness between CLI and desktop app eliminate trade-offs?
Google Antigravity 2.0 uses the exact same underlying agent harness for both the CLI and desktop app, meaning any enhancement shipped to the core agent automatically lands on both surfaces simultaneously. This eliminates the need for developers to choose between command-line speed and graphical interface, as updates cascade to both without any missing functionality.
What programmatic access does the SDK provide in Antigravity 2.0?
The SDK in Antigravity 2.0 provides programmatic access to the same agent runtime that powers Google's internal teams and the desktop application. This allows developers to build custom solutions with the full capabilities of the core agent harness without limitations.
Why is the CLI considered more than just a nostalgic holdover in Antigravity 2.0?
The CLI is not merely preserved for backward compatibility; it runs on the same engine as the desktop app and Google's internal teams use. This architectural parity ensures the CLI receives the same updates and improvements as the graphical interface, making it a first-class development tool rather than a legacy component.
Further Reading
- Google is making Gemini CLI users switch to its new Antigravity 2.0 — TechRadar
- Google Antigravity CLI — Google Antigravity Blog
- Choosing Antigravity or Gemini CLI — Google Cloud Blog
- FIRST LOOK into Google Antigravity CLI — YouTube
- How to Install and Use Google Gemini Antigravity CLI — YouTube