Google launches Antigravity 2.0 with new desktop app and CLI tool
▼ Summary
– Google Antigravity 2.0 introduces a new desktop app, CLI tool, and SDK for custom workflows, enabling users to orchestrate multiple agents, design custom subagent workflows, and schedule background tasks.
– The update is powered by the new Gemini 3.5 Flash model, which was co-developed using Antigravity.
– Native voice command support is added to Antigravity, and a new CLI tool is launched for terminal-based agent creation, with a request for Gemini CLI users to migrate.
– The Antigravity SDK allows developers to build custom agents, and Google Cloud customers can connect to Antigravity for projects, with custom agent templates available in AI Studio.
– Google introduces a new AI Ultra plan at $100 with 5x higher AI limits than the Pro plan, and reduces the top AI Ultra plan price from $250 to $200 for 20x higher limits.
Google is rolling out Google Antigravity 2.0, the latest iteration of its agentic coding platform, featuring a redesigned desktop application, a dedicated CLI tool, and a new SDK for building custom workflows. Originally launched last year to compete with tools like Cursor, Antigravity is now being upgraded with significant new capabilities.
With the updated desktop app, users can now orchestrate multiple agents simultaneously, execute tasks in parallel, design custom subagent workflows, and schedule background tasks that run automatically. The app also offers seamless integration with Google AI Studio, Android, and Firebase, making it easier to connect projects across Google’s ecosystem.
Much of this functionality is powered by the newly introduced Gemini 3.5 Flash model, which Google says was co-developed using Antigravity itself.
Voice control is also coming to Antigravity, mirroring the native voice command features already available in Gmail and Docs. For developers who prefer terminal-based workflows, Google is launching a new Antigravity CLI tool, and users of the older Gemini CLI are being encouraged to migrate.
The company is also releasing an Antigravity SDK, enabling developers to build custom agents tailored to their needs. Google Cloud customers will be able to connect to Antigravity for project development, and custom agent templates will be made available in AI Studio for enterprise users.
Additionally, Google is introducing an Antigravity export tool within AI Studio, allowing developers to export existing projects and continue working locally.
Antigravity’s coding capabilities are also being integrated into consumer products. In Google Search, for example, users will see a custom UI generated in real time as part of their search results, letting them build mini-apps while exploring a topic.
On the pricing front, Google is launching a new AI Ultra plan at $100 per month, offering 5x higher AI limits than the Pro plan. Meanwhile, the top-tier plan has been reduced from $250 to $200 per month, providing 20x higher limits. This tiered approach mirrors similar pricing strategies from Anthropic and OpenAI, both of which have introduced $100 and $200 monthly plans to accommodate varying levels of AI usage.
(Source: TechCrunch)
