Google Antigravity 2.0

The standalone command center for agent-first development

New: Changes to Antigravity Plans

Powered byGemini 3.5 FlashBuilt for real-time agent orchestration

Dynamic Subagents · Scheduled Tasks · Projects + Worktree · Artifacts

Download Free Learn More

Antigravity 2.0 Core Capabilities

A standalone, agent-first workspace for launching, orchestrating, and verifying autonomous work across projects.

Delegate complex work in parallel with dynamically instantiated subagents that accelerate end-to-end delivery.

Automate recurring checks with cron-based tasks so agents run while you are away and report back with artifacts.

Speak naturally to your agents with real-time transcription powered by Gemini audio models.

Run agents across one or more folders with project-level settings, bounded access, and persistent permission trust.

Review task-level deliverables, verification output, and feedback loops from one central command center.

Built for developers

for the agent-first era

Google Antigravity is built for user trust, whether you're a professional developer working in a large enterprise codebase, a hobbyist vibe-coding in their spare time, or anyone in between.

Frontend Developer

Streamline UX development by leveraging browser-in-the-loop agents to automate repetitive tasks.

Full Stack Developer

Build production-ready applications with confidence with thoroughly designed artifacts and comprehensive verification tests.

Enterprise Developer

Streamline operations and reduce context switching by orchestrating agents across projects and folders with Mission Control.

Meet Google Antigravity 2.0, the standalone workspace for AI agents

Antigravity 2.0 moves beyond the old repository-centric workflow into a project-centric model where agents can work across folders, tools, and tasks with clearer boundaries.

You can dual-wield Antigravity 2.0 with your IDE of choice while using Gemini 3.5 Flash, dynamic subagents, and scheduled automation to handle complex end-to-end software work.

Core Tenets

Our first product that brings four key tenets of collaborative development together

Trust

Antigravity provides context on agentic work at a more natural task-level abstraction, with the necessary and sufficient set of artifacts and verification results, for the user to gain trust.

Autonomy

Agents can operate across all surfaces simultaneously and autonomously, with a form factor that exposes this autonomy optimally and allows users to interact asynchronously.

Feedback

Intuitive async user feedback across every surface and Artifact, whether it be Google-doc-style comments on text Artifacts or select-and-comment feedback on screenshots.

Self-improvement

Antigravity treats learning as a core primitive, with agent actions both retrieving from and contributing to a knowledge base for continuous improvement.

Product Features

Comprehensive tools for the modern developer

Antigravity 2.0

NEW

Antigravity 2.0

Your command center to manage multiple local agents in parallel. Group conversations into Projects, operate across multiple workspaces, and automate routine tasks with scheduled messages.

Antigravity CLI

NEW

Antigravity CLI

The lightweight, fast, terminal-first surface to work with Antigravity agents. Run autonomous coding agents, execute shell commands directly, and manage background subagents all from your keyboard.

Antigravity SDK

NEW

Antigravity SDK

Prototype custom agents leveraging Antigravity's harness with minimal code. Simple Python scripts to iterate on agentic applications, automate software engineering tasks, and run evaluations on top of the Antigravity agent harness.

Antigravity IDE

NEW

Antigravity IDE

The fully-featured, agentic IDE. Complete with the agent manager, artifacts, and a deep understanding of your codebase.

Watch Antigravity in action

Product demos and launch videos covering Antigravity 2.0, CLI, SDK, and IDE workflows.

Frequently Asked Questions

Everything you need to know about Google Antigravity 2.0

Antigravity 2.0 is a standalone desktop application for launching, monitoring, and orchestrating AI agents across projects. It is designed as a central command center for agent-first development.

Antigravity 2.0 is separate from the IDE. You can use it alongside your preferred editor in a dual-wield workflow: the IDE for code editing and Antigravity 2.0 for agent orchestration.

Gemini 3.5 Flash powers key Antigravity 2.0 flows such as scheduled automation and fast agent interactions, while additional reasoning models can be selected where supported.

Scheduled Tasks let you send timed instructions to your agents with cron-style scheduling so work can run automatically in the background and report results later.

Agents run inside Projects with folder boundaries, scoped settings, and scoped permission grants. This gives you safer control over what each project can access.