Google Antigravity 2.0: The Full Developer Information

Google didn’t simply ship an replace at I/O 2026. They redrew the map. 

Google Antigravity 2.0 dropped on Might 19^th and it’s not an IDE refresh. It’s a full platform pivot from AI assisted coding, to multi agent orchestration because the core improvement mannequin. In the event you’ve been keeping track of the Agentic coding race between Cursor, GitHub Copilot, and everybody else, Google’s right here with its two cents.

What Is Google Antigravity?

Antigravity was first launched in November 2025, with Gemini 3, as a solution from Google as to what it might provide when it got here to a free IDE for brokers. It was a succesful product however its scope was restricted. This offered the consumer with a wise coding assistant inside a well-recognized interface. 

Antigravity 2.0 has been fully rebuilt by Google as a standalone desktop software that has no ties to Antigravity 1.0. As an alternative, the two.0 model was created and designed from the bottom as much as assist agent orchestration performance. Antigravity 1.0 continues to be accessible to be used, however Antigravity 2.0 has turn out to be their new flagship product. Antigravity 2.0 was constructed for a workflow the place the consumer will direct brokers, versus prompting an auto-complete engine.

The pitch of Antigravity hasn’t modified, which continues to be you could take an concept, and ship it as a manufacturing app. The principle distinction is that there’s additionally a CLI, SDK and managed cloud brokers now which supplies the consumer much more floor space than was supplied with Antigravity 1.0. 

Key Options of Antigravity 2.0

The standout options of Antigravity 2.0 are: 

1. The Standalone Desktop App 

The brand new desktop software will function the principle function of the discharge. This software serves as your main hub for coordinating a number of brokers that run concurrently, in addition to for creating customized workflows for sub-agents and for scheduling duties that might be carried out routinely within the background. 

The scheduled job’s perform is a type of issues that may simply be neglected; nevertheless, it’s fairly revolutionary. Beforehand, in the event you needed an agent to carry out a job for you, you would need to immediate the agent every time you needed the duty carried out. Now, by creating one job setup and giving the agent the power to do it routinely, the agent is now extra like a steady background course of. 

Moreover, there are native voice instructions that you need to use to regulate Antigravity 2.0. It might not appear to be a big addition. Nonetheless, it’s according to the voice integration being applied into Gmail and Docs, due to this fact it matches nicely. 

2. The Antigravity CLI 

For builders who kinda favor the terminal, Google constructed a model new Antigravity CLI from scratch in Go. It strikes faster than what got here earlier than. And it absolutely replaces the Gemini CLI which is getting retired.   

For client entry to Gemini CLI, there’s an finish date June 18, 2026, for AI Professional, AI Extremely, and free-tier customers. This isn’t a delicate deprecation, however extra like a tough cutoff.   

The CLI retains the Gemini CLI bits builders used, Agent Abilities, Hooks, Subagents, and Extensions (however now they’re renamed Antigravity plugins). The principle factor to understand is that the CLI and the desktop app run on the identical underlying agent harness. So, any enhancements Google ships into the core brokers, they land on each surfaces routinely. You don’t have to choose one and lose out on the continuing updates to the opposite. 

3. The Antigravity SDK 

With the SDK you get programmatic entry to the identical agent harness that powers Googles inside stuff, you understand. It’s designed for Gemini fashions, and it allows you to form customized agent behaviors, then run them wherever your individual infrastructure lives. Principally, that is the selection for engineering groups that need Antigravity-style brokers embedded into their merchandise, with out having to depend on Googles cloud. 

4. Managed Brokers within the Gemini API

That is the function that, truthfully, will get probably the most use with backend builders. With only one API name, you possibly can spin up an agent that causes after which makes use of instruments, then it executes code in an remoted Linux place.   

Three issues make it work:   

• Antigravity agent harness: The identical form of know-how Google makes use of internally, co-optimized with Gemini 3.5 Flash.   
• Persistent remoted environments: Each time you work together, it creates an setting you possibly can resume later in follow-up calls. The recordsdata and the state keep intact between turns, like no resets.   
• Customized agent definitions: You possibly can lengthen the bottom agent by utilizing markdown talent recordsdata, and there are new agent templates within the Google AI Studio Playground that allow you to begin quick, kinda instantly. 

5. Antigravity within the Gemini Enterprise Agent Platform 

In case you are a buyer of Google Cloud, the enterprise path permits you to join Antigravity on to your present Google Cloud initiatives. That is vital for groups needing agent workflows which can be inside their present cloud infrastructure, in addition to having applicable entry controls and a whole audit path. 

The Mannequin Working It All: Gemini 3.5 Flash

Entire Antigravity 2.0 eco system simply defaults to Gemini 3.5 Flash. Per Google, it beats Gemini 3.1 Professional on most benchmarks too, and it’s roughly 4 instances faster than different frontier fashions. That hole issues loads as soon as you start working a number of parallel brokers, as a result of mannequin latency doesn’t keep put. It form of stacks up quick.  

Even a 200ms distinction per name turns into a number of seconds of lag when ten brokers are firing on the similar time. Additionally, Gemini 3.5 Flash wasn’t inbuilt some completely separate manner: it was co-developed utilizing Antigravity itself. Google’s group used the exact same agentic workflows they’re now rolling out to everybody. 

Getting Began with Antigravity 2.0

Step 1: Obtain  

Go over to antigravity.google/obtain, seize the installer on your OS, and run it. 

Step 2: Onboarding  

Launch the app and click on by means of the setup, when it asks about agent mode, select Overview-Pushed Growth (beneficial). This one lets the agent transfer by itself however it nonetheless asks on your approval earlier than something “huge” occurs, like significant modifications.

Step 3: Check in  

Check in utilizing your Google account. On the free tier you get entry to Gemini 3.1 Professional, Claude Sonnet 4.5, and gpt-oss, principally. 

Step 4: Open a workspace  

Click on Open Folder and choose your challenge listing. It’s best to land within the Agent Supervisor, consider it as your mission-control for all agent exercise.

Step 5: Set up the browser extension  

In order for you the agent to browse the net, give it a job with a URL (like go to antigravity.google). It would ask you to put in the Chrome extension. Hit Setup and simply observe the on-screen circulation. 

Step 6: Begin a dialog  

Press Begin Dialog, sort your job, and choose your agent mode. For complicated multi-file work, select Plan. For fast one-liners select Quick, no have to overthink. You can even use @filename to connect particular recordsdata as additional context. 

Because it runs, the agent creates Artifacts: job lists, implementation plans, code diffs. You evaluation these in Agent Supervisor, add feedback if wanted, or approve so it continues. 

Fingers-On: Construct a To-Do App from Scratch

Constructing: A FastAPI backend to permit including, itemizing and deleting objects together with an HTML and JS entrance finish. 

1. Utilizing Agent Supervisor, begin a brand new dialog within the workspace and change to Plan mode. 

2. Enter the next immediate: 

“Create a to-do software with FastAPI because the backend and plain HTML and Javascript because the entrance finish. The endpoints are: 
- add a job 
- listing all duties 
- delete a job utilizing its ID. 
All duties might be saved in reminiscence. Present a necessities.txt file.”

3. Overview plans made by the agent to create the Process Checklist and Implementation Plan earlier than any recordsdata have been created. If it’s good to make any modifications, add feedback; if okay, press the approve button. 

4. Because the App builds, watch the recordsdata be added in real-time beneath Editor. The next recordsdata might be created: important.py, index.html, necessities.txt. To view recordsdata as they’re created, click on on the Editor tab. 

5. Execute app. To search out actual command used to run agent’s first file, view agent’s Walkthrough artifact: it’ll appear to be: 

uvicorn important:app –reload