Google Antigravity

Google Antigravity is an agentic development platform for autonomous agents across app, CLI, IDE, and SDK surfaces. Windows download, free plan, Pro, Ultra, and Google Cloud access.

Desarrollo Agentes IA Herramientas IA Dev Agente de Programación

Visitar Sitio Web

Overview

Google Antigravity is an agentic development platform for working with autonomous coding agents across the app, terminal, IDE, and SDK surfaces. The site positions it as a tool for developers in the agent-first era, with a Windows download and product tiers that cover individual users, teams, and Google Cloud customers.

At the product level, Antigravity is built around orchestrating multiple agents in parallel, reviewing artifacts and verification results, and steering work through feedback rather than manual step-by-step execution. The product pages split the experience into Antigravity 2.0 for multi-agent coordination, Antigravity CLI for terminal-first work, Antigravity SDK for prototyping custom agents, and Antigravity IDE for a fuller editor experience.

Core capabilities

Parallel agent orchestration

Work with several autonomous agents at once, including background subagents that handle parallel tasks while you continue elsewhere.

Project-based workspace management

Organize work into Projects, span multiple folders, and apply scoped settings and permissions where needed.

Scheduled automation

Define routine jobs as scheduled tasks so agents can run checks and other work automatically in the background.

Artifacts and verification

Use artifacts and verification outcomes to track what the agent did and review deliverables at a task level.

Extensible agent behavior

Customize behavior through skills, MCPs, and JSON hooks at the global or workspace level.

Multiple control surfaces

Use natural-language prompts, terminal shortcuts, and slash commands to steer work without leaving the workflow surface.

Practical use cases

Parallel development work
Coordinate several agents on independent pieces of a larger coding effort, then use artifacts and verification results to review progress before merging the work.
Terminal-first coding
Use the CLI when you want to stay in the terminal, trigger autonomous agents, run shell commands, and monitor background subagents without switching contexts.
Custom agent prototypes
Prototype agentic applications in Python using the SDK, then iterate on automation logic or evaluation runs on top of the Antigravity harness.
Agent-assisted IDE workflows
Use the IDE when you want a more complete editor surface with agent management and codebase awareness for ongoing implementation work.
Team and organization usage
Apply the platform to enterprise or team settings where work spans multiple workspaces, requires scoped permissions, or benefits from organization-level access through Google Cloud.

Pros and Cons

Pros

Supports multiple agent-oriented surfaces: app, CLI, IDE, and SDK.
Lets users orchestrate parallel agents and background subagents for larger tasks.
Includes artifacts and verification outcomes to make agent work easier to review.
Offers customization through skills, MCPs, and JSON hooks.
Provides a pricing path for individuals, Pro and Ultra users, and Google Cloud organizations.

Cons

The source does not publish detailed platform support beyond Windows download links.
The coverage available here is partial, so integrations, setup steps, and system requirements are not fully documented on the captured pages.
Pricing and access details vary by plan, but the source does not provide a full limit table or exact usage caps.

FAQ

What is Google Antigravity?

Google Antigravity is an agentic development platform with product surfaces for the main app, a terminal-first CLI, an IDE, and an SDK. The homepage positions it for developers working in the agent-first era, while the pricing page shows separate individual, Pro, Ultra, and organization access paths.

What platforms or access paths are available?

The source shows a Windows download flow for Google Antigravity, with separate downloads for x64 and ARM64. The pricing page also notes that Google Cloud customers can access Antigravity 2.0 and CLI through the Gemini Enterprise Agent Platform.

How do Antigravity 2.0 and Antigravity CLI differ?

The homepage and product pages describe Antigravity 2.0 as a command center for managing multiple local agents in parallel, with Projects, scheduled tasks, artifacts, and dynamic subagents. The CLI is the terminal-first surface for running autonomous agents, executing shell commands, and managing background subagents.

What pricing options are described?

The pricing page lists access to Gemini 3.5 Flash, Gemini 3.1 Pro, Gemini 3 Flash, Claude Sonnet and Opus 4.6, and gpt-oss-120b for Individual plans, with higher access and a flexible AI credit pool on higher tiers. The organization plan is described as available via Google Cloud with consumption-based API pricing.

What should users know before adopting it?

The source does not provide full setup details, system requirements, or integration lists. It does show that the CLI supports slash commands, /agents, /config, and /keybindings, and that the platform includes skills, MCPs, and JSON hooks in its customization model.

Quick Facts

Category: Developer Tool
Primary users: Developers and teams working with autonomous agents
Source domain: antigravity.google
Platform support shown: Windows download, including x64 and ARM64
Access model: Free individual plan plus Pro, Ultra, and organization access paths
Core workflow: Orchestrate agents, review artifacts, and automate tasks