Google Antigravity

Google Antigravity
DeveloperGoogle
Initial release1.11.2 public preview [1]/November 18, 2025 (2025-11-18)
Preview release
1.12.4[2]  / 17 December 2025 (17 December 2025)
Platform64-bit Windows 10 or later, macOS Monterey 12 or later, 64-bit Linux with glibc 2.28 or later and glibcxx 3.4.25 or later [3][4]
TypeIDE, artificial intelligence
LicenseProprietary (free during preview)
Websiteantigravity.google

Google Antigravity is an AI-powered integrated development environment (IDE) developed by Google, designed for prioritizing AI agents platform for software development. Announced on November 18, 2025 alongside the release of Gemini 3, Antigravity enables developers to delegate complex coding tasks to autonomous AI agents powered primarily by Google's Gemini 3 Pro [5], Gemini 3 Deep Think (also called Gemini 3 Pro (High)) and Gemini 3 Flash models.[6] The platform is built as a fork of Visual Studio Code, with debate whether it is a direct fork of it, or an indirect fork of it because it is a fork of Windsurf which is itself a fork of Visual Studio Code[7]. Google Antigravity supports multiple AI models, including Anthropic's Claude Sonnet 4.5 and Claude Opus 4.5, as well as open-source variant of OpenAI models (GPT-OSS-120B).[8]

Antigravity was released in public preview on the day of its announcement and is available free of charge for Microsoft Windows, macOS, and Linux, with "generous rate limits" for Gemini 3 Pro usage.[5]

Features

Antigravity introduces an "agent-first" paradigm, shifting from traditional AI code assistance to a system where AI agents operate with greater autonomy. It features two primary views:

  • Editor view: A usual IDE interface like Visual Studio Code and PyCharm with an agent sidebar, similar to tools like Cursor or GitHub Copilot.
  • Manager view: A control center for orchestrating multiple agents working in parallel across workspaces, allowing asynchronous task execution.[9]

To build user trust, agents generate "Artifacts" - verifiable deliverables such as task lists, implementation plans, screenshots, and browser recordings - rather than raw tool calls.[10] Agents have direct access to the editor, terminal, and a integrated browser, and can learn from previous interactions.[11]

References

  1. ^ "Google Antigravity".
  2. ^ https://antigravity.google/changelog. {{cite web}}: Missing or empty |title= (help)
  3. ^ "How to Download and Install Google's Antigravity IDE | Second Talent". 2025-11-19. Retrieved 2025-11-22.
  4. ^ "Google Antigravity". Google Antigravity. Retrieved 2025-11-22.
  5. ^ a b Preston, Dominic (2025-11-18). "Google Antigravity is an 'agent-first' coding tool built for Gemini 3". The Verge. Retrieved 2025-11-18.
  6. ^ "Gemini 3 Flash: Frontier intelligence built for speed".
  7. ^ "Google's Antigravity IDE Sparks Forking Debate -".
  8. ^ Brandom, Russell (2025-11-18). "Google launches Gemini 3 with new coding app and record benchmark scores". TechCrunch. Retrieved 2025-11-18.
  9. ^ "Google Antigravity introduces agent-first architecture for asynchronous, verifiable coding workflows". VentureBeat. November 18, 2025. Retrieved November 18, 2025.
  10. ^ "Antigravity Is Google's New Agentic Development Platform". The New Stack. November 18, 2025. Retrieved November 18, 2025.
  11. ^ Whitwam, Ryan (2025-11-18). "Google unveils Gemini 3 AI model and AI-first IDE called Antigravity". Ars Technica. Retrieved 2025-11-18.
This article is issued from Wikipedia. The text is available under Creative Commons Attribution-Share Alike 4.0 unless otherwise noted. Additional terms may apply for the media files.