Google launches Antigravity 2.0 with AI agents orchestration, but CLI shift sparks controversy

Google launches Antigravity 2.0 with an updated desktop app and CLI tool | TechCrunch

Google is introducing a new version of its agentic coding app, Google Antigravity 2.0, with an updated desktop app, a CLI tool, and an SDK for custom workflows. The company launched its Antigravity tool last year as a response to agentic coding software such as Cursor. The company said that with the new desktop app, users can orchestrate multiple agents and execute tasks simultaneously. Plus, you can design custom subagent workflows and schedule tasks that can automatically run in the background. The new app also easily lets you integrate projects with Google AI Studio, Android, and Firebase. A lot of this is powered by the company's new Gemini 3.5 Flash model, which was co-developed using Antigravity, Google said. Google is also adding native voice command support to Antigravity, just like it has added to multiple consumer products, including Gmail and Docs. And it's launching a new Antigravity CLI (Command Line Interface) tool for programmers who want to use a terminal for creating agents. Google is asking users who used the Gemini CLI tool to migrate to the new tool. What's more, Google is launching an Antigravity SDK for developers to build custom agents based on Google's coding tool. The company will allow Google Cloud customers to connect to Antigravity to build projects. It noted that it will release custom agent templates in AI Studio for enterprise users to get started. Google is also adding an Antigravity export tool to AI Studio for developers to export their existing project and carry on the work locally. Google is using Antigravity's coding chops in consumer products like Search, where users will get a custom UI generated in real-time as part of an answer. Here, users will be able to build mini-apps while exploring a topic within search, the company said. The company is introducing a new AI Ultra plan priced at $100, offering 5x higher AI limits in Antigravity than the Pro plan. It 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. Other AI labs, including Anthropic and OpenAI, have added both $100 and $200 per month plans in the last few years to create a tiered system for users with different AI usage requirements.

Bye-bye, Gemini CLI; Google's gone and swapped you for a closed-source AI

Pour one out for the Gemini Command Line Interface. Come June 18, the open source development agent will stop serving most users in favor of the new Antigravity CLI, and developers aren't happy that the replacement is far less open than the old tool. Google announced the Antigravity CLI at Google I/O this week, billing it as a way for the Chocolate Factory to unify its efforts in developing a command line interface for AI agents. One of the key arguments Google makes in a post about transitioning from Gemini CLI to Antigravity CLI is that the new one has improved support for multi-agent environments, but the company isn't giving most of its users much of a choice on whether to switch. "On June 18, 2026, Gemini CLI and Gemini Code Assist IDE extensions will stop serving requests for Google AI Pro and Ultra, as well as those using it free of charge using Gemini Code Assist for individuals," the Gemini CLI team wrote in their announcement of the transition. The change also affects Gemini Code Assist for GitHub, which won't allow new installations beginning June 18, and will stop serving requests in the following weeks. Enterprises appear to be getting a pass, however, with Google noting that those using Gemini CLI or its IDE extensions through a Gemini Code Assist Standard or Enterprise license won't see any changes in their access, nor will Gemini Code Assist for GitHub users accessing the tools through their enterprise Google Cloud accounts. "Gemini CLI will remain accessible via paid Gemini and Gemini Enterprise Agent Platform API keys," Google explained. For everyone else, sorry: It's Antigravity CLI or bust, but don't expect the same experience. "There won't be 1:1 feature parity right out of the gate" between Gemini CLI and Antigravity CLI, Google added. Agent skills, hooks, subagents, and extensions are all being supported by Antigravity CLI at launch. But other stuff may take time to arrive, if it does at all. Take a look at the Gemini CLI GitHub page, and you'll find all the code that made it possible - it is an open-source project, after all. Surf over to the Antigravity CLI GitHub page and all you'll see is a change log, readme, and a GIF file demonstrating the tool's appearance. That's right: Antigravity CLI isn't open source - at least not from what Google has published so far - and it took developers no time at all to notice. Gemini CLI Lead Product Manager Dmitry Lyalin took to GitHub to make an announcement detailing some additional info about the forced CLI tool migration, and the comments are rife with people frustrated by the move. No small portion of the vitriol is targeted at apparent usage limits, with multiple people reporting they'd hit their weekly quota with just a couple of requests. The issues page for Antigravity CLI similarly has numerous posts asking Google to look into usage limits. Other posts accuse Google of using open-source contributions to improve a new closed-source product and generally express frustration with Google for killing yet another thing customers relied on. At the same time, Lyalin teased developers by telling them that, no, Gemini CLI isn't truly gone if you're willing to pay top dollar for it. "The project remains available to the community as an Apache 2.0 licensed repository with no changes," Lyalin noted in his GitHub post. "You will continue to see us work on GitHub as we keep Gemini CLI updated with latest model releases, bugs and security fixes for our enterprise customers." Now please open your wallets if you want access to this open-source product. Google didn't respond to questions for this story. ®

Google flips Antigravity into an agentic dev suite, AI Studio app lands on Android

With Gemini 3.5 Flash doing frontier-level work at a fraction of the cost, Google's Antigravity 2.0 is here to help build and manage your agents and let them loose on your latest projects. Meanwhile, AI Studio is gaining a dedicated Android app to execute on your ideas while on the go. Google first introduced Antigravity last year at the onset of the vibecoding era. In the months since, Antigravity has existed as a dedicated application that borrows heavily from Microsoft's VS Code but significantly integrates AI coding assistance. With this latest suite of announcements, Google has repositioned Antigravity as something of a unified brand for AI coding harnesses fit for the agentic future. This starts with version 2.0 of the main Antigravity application, which puts agent orchestration front and center. Rather than performing one task at a time, you can set agents to work on several problems in parallel, multiplying your development velocity. The Antigravity revamp also brings in new integrations across Google AI Studio, Firebase, and Android. For example, you can now export projects from AI Studio directly to your local Antigravity app, carrying over all of your context to resume agentic development locally. Next up, for developers who would rather stay in their IDE of choice, Google is launching a new CLI for Antigravity. With it, you'll be able to kick off new agents without leaving the terminal. Curiously, the Antigravity CLI is set to fully replace the previous Gemini CLI, meaning developers will need to migrate any of their existing agentic workflows to the new tool. Taking things a step further, you can also use the new Antigravity SDK to create custom agents optimized for Gemini. Once built, you can deploy your Antigravity agents on the infrastructure that works best for your organization or use case. To streamline this process even further, Google is also launching a new "Managed Agents" feature in the Gemini API, offering your agents an "isolated Linux environment" in which to perform their work. Of course, coding agents are more taxing on your token budgets than traditional chat experiences like Gemini. Developers may find themselves needing more than what the $20 per month Pro plan provides but unwilling to jump up to the top tier. To that end, Google is launching a new $100 per month tier of AI Ultra, offering 5X the usage limits in Antigravity compared to AI Pro. As a special offer for I/O week (until May 25, 2026), new and existing AI Ultra subscribers can claim $100 of bonus credits to help ensure work doesn't cease if you run against your quota. Overall, this expansion of Antigravity seems poised to help Google regain some ground in the battle for developer demand for AI tools. Google's offerings should be especially enticing in light of the significant coding capability improvements of Gemini 3.5 Flash, as the model can perform many of the same tasks as frontier models at a fraction of the cost and output the code far faster. Multiply those speed gains across several Antigravity agents, and your ideas can come to life in minutes. In related news, Google is also launching a dedicated Android application for AI Studio. Details are currently limited, but it seems you'll be able to speak or type ideas into AI Studio or start from high-quality example apps. Once completed, you'll be able to share apps directly with friends, bringing a social element to the experience. You can pre-register for AI Studio today in the Play Store. Your next big idea is just a conversation away. Inspiration doesn't wait for you to be at your desk. It strikes on the couch, on the bus, or in the middle of the night. With Google AI Studio, you finally have a way to capture that spark and turn it into something real -- right from your phone. Bringing it all together, Google is enabling developers to act on their ideas from anywhere that inspiration strikes. Explain your vision to AI Studio on your phone and return home to find a full-fledged prototype. From there, you can export the project to Antigravity to launch more agents on your own machine. It's a workflow that makes app development feel less like coding and more like project management, leading a team of Gemini-powered AI agents.

Google accelerates agent-native software development with expanded Antigravity platform - SiliconANGLE

Google accelerates agent-native software development with expanded Antigravity platform Google Cloud is enhancing its "agent-first" coding platform for developers with the launch of Antigravity 2.0, a new standalone desktop application that enables a full "agent-optimized" user experience. It comes alongside the debut of Managed Agents in the Gemini application programming interface and native Android vibe coding in Google AI Studio, which were also announced today. The updates arrived during Google I/O today, building upon November's launch of the original Antigravity platform that's designed to support artificial intelligence automation at a higher, task-oriented level. With Antigravity, AI evolves from an assistant to a true collaborator that's able to work on its own initiative and with minimal supervision. The platform takes the appearance of a standard coding environment, but it's peppered with AI agents that can access everything from the editor to the terminal and even an integrated web browser. This means they have all of the tools required to autonomously plan and execute complex programming tasks. The original Antigravity was powered primarily by Gemini 3 Pro, later upgraded to Gemini 3.1 Pro, and from today, users will now have access to Google's most advanced Gemini 3.5 Flash model. In a blog post, Google DeepMind Director of Software Engineering Varun Mohan noted that 3.5 Flash outperforms Gemini 3.1 Pro on almost all coding benchmarks while running four times faster than any other frontier model, giving developers the "high-speed engine needed for real-world agentic workflows." Antigravity 2.0 is meant to act as a central home for agentic interactions, enabling developers to orchestrate multiple AI agents that can perform tasks in parallel. It also introduces "dynamic subagents," which are for parallelized workflows, scheduled tasks for background automation and new integrations with Google AI Studio, Android and the Firebase mobile development platform. Developers may prefer a traditional terminal-style experience when the embark on agentic development, and they're also catered to with Antigravity CLI. It's a new and lightweight yet high-velocity product surface where agents can be created instantly without the need for a graphical user interface. Finally, Google also revealed the new Antigravity SDK, which provides programmatic access to the same agents found in Antigravity, enabling users to define custom agent behaviors and host them on third-party infrastructure. Sticking with agentic development, Google said it's updating the Gemini API for integrating AI capabilities into software applications with the introduction of Managed Agents. Mohan explained that Managed Agents made it possible to spin up new agents that can reason, use third-party tools and execute code in isolated Linux environments with a single API call. These Managed Agents are all powered by the Antigravity agent harness and Gemini 3.5 Flash, and can be accessed through the Interactions API and through Google AI Studio. Because they use Antigravity's harness, it means that user's custom built agents will be based on the same technology and infrastructure as Google's own agents. Developers can get started building custom agents using Google's new agent templates, and will also be able to extend the capabilities of their Managed Agents with customized instructions and skills using markdown files. Another way for developers to access the latest capabilities of Gemini 3.5 Flash is through the Google AI Studio, which is a web-based prototyping environment that makes it simple to experiment with AI, refine prompts and generate API keys. Google AI Studio is now powered by Antigravity's coding agents too, and the company said it's expanding the ways developers can use the platform. For instance, there's a new mobile application opening for registration now that sacrifices deeper functionality for convenience, allowing developers to "capture an idea on the go and have a working prototype ready by the time you get to your desk," Mohan said. Additionally, Google AI Studio is now integrated with Google Workspace, which means AI agents will be able to call relevant Workspace APIs and embed them directly into apps built using the platform. Should developers decide they need more advanced coding functionality, they can now export their entire Google AI Studio projects to the locally-hosted Antigravity platform with a single click. Finally, there's a new integration that makes it possible to build native Android applications with a single prompt. Once satisfied, developers will be able to publish their apps directly in the test track within the Google Play Console. The last major dev-focused update pertained to the Gemini Enterprise Agent Platform, formerly known as Vertex AI, which is the company's full-stack development platform for building enterprise-grade AI agents and autonomous applications that can plan and execute complex, multistep tasks. The main update here is all about securing agent-generated code. It's called CodeMender, a newly integrated AI code security agent that was first created by Google DeepMind researchers. By leveraging Agent Platform's capabilities and the most advanced Gemini models, it autonomously searches for and identifies any vulnerabilities in newly created code, including that generated by other agents. Once a bug is identified, CodeMender will recommend a precise fix, apply it on command and then securely test the code to ensure there are no more loopholes or weaknesses.

Antigravity 2.0 Gets Real in Competing with Claude Code and Codex

Google I/O 2026 just took place last night as per India's time. During the event, Sundar Pichai took the stage to announce some pretty exciting updates from Google centered around AI (artificial intelligence). One of the huge updates was around Antigravity. Google's Antigravity 2.0 is here, and this time, it is not just an IDE application. Google's Antigravity 2.0 is now a standalone app, which is more like what Anthropic did with Claude Code and OpenAI did with Codex. Developers are drooling over Claude Code and Codex for months now. Thus, Antigravity 2.0 sounds like an exciting update for the users. It is now available for macOS, Linux, and Windows platforms. Further, the Antigravity 2.0 now runs on Gemini 3.5 Flash. What's great here, if you don't know is just good Gemini 3.5 Flash really is. Google said that Gemini 3.5 Flash beats Google's own Gemini 3.1 Pro on coding and agentic benchmarks.

Google I/O 2026: Antigravity is putting AI on steroids these 5 ways

Among the more surprising revelations from I/O is that Gemini CLI is being retired. When Google released Gemini CLI last year, its purpose was to make Gemini available right inside the terminal. Having garnered over 100,000 stars on GitHub, 6,000 merged pull requests, and millions of users, Google claims the tool has simply been outgrown. The issue is not about popularity but rather scope. Users increasingly need to employ multiple agents that can communicate with each other and divide the workload and resolve complex issues, something that requires terminal tools to operate on a common backend with everything else developers are doing. Also read: Google wants to compete with Claude Mythos with its new CodeMender, here is how Antigravity CLI is the new tool, and it's much more than just a rebranded version of the old one. Antigravity CLI is built in Go and is therefore more responsive and faster, offers asynchronous workflows to control multiple agents in the background, and uses the same agent harness as Antigravity 2.0, ensuring that any improvement to core agents will apply to both products at once. The migration period ends on June 18, 2026, after which Gemini CLI and Gemini Code Assist IDE extensions will no longer process requests from Google AI Pro and Ultra customers, as well as those using the free tier. Now, the five ways Antigravity is changing the game. Antigravity 2.0 is the new stand-alone desktop application optimized for the agent experience. It serves as the main hub where you interact with multiple agents running parallel tasks, dynamic subagents for parallelizing tasks, scheduled tasks for background automation, and ecosystem integration from Google AI Studio, Android, and Firebase. Imagine this as not just an interface but a command center where you could run a massive code refactoring project along with some research work concurrently without worrying about locking your entire workflow. The introduction of the Managed Agents in the Gemini API means that you can now create an agent that can reason, use tools, and execute code in an isolated Linux environment with one API call. Every conversation spawns an environment that can be used further in subsequent calls while retaining everything that was done previously. This is Google's infrastructure move where it gives developers the same agent harness that it uses internally, which is co-optimized with Gemini 3.5 Flash. You can even extend the agent with custom instructions and skills using markdown files as new custom agent templates are being provided in the Google AI Studio Playground. Also read: Google Search gets big upgrades: Agentic coding, Search agents, expanded personal intelligence and more in Google I/O 2026 None of this will work unless the underlying model is fast enough to handle it. Gemini 3.5 Flash beats Gemini 3.1 Pro across almost all benchmark tests while being four times faster than other frontier models, which is exactly what you want when implementing agentic workflows that involve agents waiting on each other in chains. That's the distinction between an AI assistant and an AI workforce. The Google AI Studio mobile application, which you can pre-register for, will enable you to capture your idea while on-the-go and create a working prototype before you even sit down at your desk. This represents a true change in the beginning of the development loop. Furthermore, agents can now make native calls to Google Workspace APIs and integrate them in their applications, and entire projects can be exported to local development in Antigravity in one click, while preserving the full project context. Moreover, there's native Android support, meaning that developers can now create top-notch Android applications using prompts alone, and publishing them straight to the Google Play Console test track from within Google AI Studio. Google is putting its money where its mouth is when it comes to the ecosystem approach. The Build with Gemini XPRIZE Hackathon offers a prize pool worth $2 million, which is the largest amount yet offered by any hackathon. In addition, developers interested in more than just hobbyist use cases will appreciate the launch of the Google AI Ultra plan, which begins at $100 a month and provides users five times the usage limits of the AI Pro plan in the Google Antigravity system. Existing and new Ultra users can receive an additional $100 in credits for a limited time until May 25, 2026. Also read: Google Project Genie can now turn real locations into interactive AI worlds: Here is how The through-line across all of this is the same: Google is done treating AI as a feature. Antigravity is a platform bet and I/O 2026 is where it officially becomes the foundation everything else is built on.

Google I/O 2026: Google claims Antigravity 2.0 created an operating system in 12 hours, brings vibe coding to Android

AI Studio now lets users create Android apps using natural language prompts and test them through an integrated emulator. As expected, Google has used I/O 2026 to double down on AI-powered announcements. The company announced a major upgrade to its agentic coding platform called Antigravity 2.0. Along with this, the company also announced new vibe coding capabilities inside Google AI Studio that will allow users to create Android apps using natural language prompts. During the keynote, Google claimed that Antigravity 2.0 was able to make the core framework of a working operating system in nearly 12 hours. The company also claimed that the AI platform launched 93 separate sub-agents during the task, processed billions of tokens, and completed the project for under $1,000 in computing costs. The company even demonstrated the system live on stage by attempting to run the classic game Doom on the AI-created OS. Initially, it failed because keyboard drivers were missing, but then the company instructed Antigravity 2.0 to generate the required drivers in real time, after which the game reportedly became functional. Also read: Google I/O 2026: Gemini 3.5 Flash, AI video tool and major Gemini app upgrades announced The platform is designed around agentic AI, where multiple autonomous AI systems divide and handle tasks. Google said that the system can independently manage the coding, planning, design and workflow related tasks without needing constant human supervision. Adding on, Google also announced a big update for its AI Studio, which introduces native Android app creation through prompts. Users can now describe an app idea in plain language and preview it inside an integrated Android emulator. Apps can also be tested directly on connected Android smartphones. The company also stated that the first version of the feature is focused on lightweight utility apps. AI-backed experiences and hardware-based applications that use device features such as cameras or GPS. However, apps generated through AI Studio will still need to pass Google Play's existing quality review and publishing guidelines before release. The company also confirmed that Antigravity 2.0 is now available as a standalone desktop application and will support command-line access for developers seeking deeper workflow integration.