Google Antigravity

Google's agent-first development environment, now a native desktop app where autonomous Gemini-based agents plan, execute, test, and refactor full-stack apps across editor, terminal, and browser.

Free tier / included with Google AI Pro ($19.99/month) and Ultra (from $99.99/month)

My take

Antigravity is a software development workbench that can also be used for knowledge work, just like Claude Code. Since the 2.0 update it looks almost exactly like the ChatGPT and Claude desktop apps, and I enjoy using it to experiment with websites. It has also become my go-to for hands-on computer tasks: it helped me troubleshoot network and power-management issues on my machine.

Visit Google Antigravity Back to tools

At a Glance

Pros

+ Fully autonomous agents that plan, execute, test, and refactor
+ Native desktop app (2.0) that feels like the ChatGPT and Claude apps
+ Gemini 3.8 Flash on every plan — fast and capable on simple-to-medium tasks
+ Orchestrates multiple agents and scheduled background tasks
+ Produces reviewable artifacts: plans, screenshots, walkthroughs
+ Surprisingly good at working directly on your computer

Cons

− The strongest models need a paid Google AI plan
− Less mature than Claude Code for complex engineering tasks
− Free-tier limits are low and Google doesn't publish exact numbers; the long-term pricing model is still settling

Best for: Vibe coding full-stack apps, static websites, games, and browser extensions with autonomous Gemini-powered agents — plus hands-on computer tasks like system troubleshooting

Powered by

Gemini 3.8 Flash multimodal Gemini 4 Argon multimodal

Full review

Google Antigravity is an agent-first development environment where autonomous Gemini-based agents handle the full development lifecycle: planning, coding, testing, and refactoring across editor, terminal, and browser. With version 2.0, it grew from a browser-based IDE into a native desktop app, joined by a CLI tool and an SDK for custom agent workflows.

The 2.0 desktop app

The new desktop app was rewritten from scratch, and it shows. It looks and feels remarkably like the ChatGPT and Claude desktop apps: a clean chat-first surface with the development machinery behind it rather than in front of it. Moving off the browser also brought faster performance and proper access to local files, and you can now orchestrate several agents at once or schedule tasks that run in the background. Voice commands and integrations with Google AI Studio, Android, and Firebase round it out.

The agent-first approach

Traditional AI coding assistants respond to individual prompts. Antigravity’s agents work autonomously. Give them a goal and they break it down into subtasks, execute them across multiple tools (editor, terminal, browser), and produce reviewable artifacts like implementation plans, screenshots, and walkthroughs.

The model underneath

Gemini 3.8 Flash is available on every plan. That’s a real trade-off. Flash lags the frontier models by a fair margin on genuinely hard problems, but it is fast, cheap, and performs well on simple-to-medium tasks — which is most of what day-to-day building actually is. The stronger models sit behind a paid plan: Claude Opus 5.5 and Sonnet 5.5 on Google AI Pro (not the trial), Ultra and Enterprise, and Gemini 4 Argon on the same plans (not in the Antigravity IDE). If you need volume and speed, Flash is a good fit; for harder problems, plan on paying.

What I’ve built and fixed

In practice, Antigravity handles a few types of work well:

Static websites: full site generation with responsive design — my favorite playground for experiments
Games: interactive browser-based games with logic and graphics
Browser extensions: Chrome extensions with manifest, content scripts, and popup UI
Computer tasks: it interacts directly with the machine it runs on. It diagnosed and fixed network and power-management issues on mine, the kind of job you’d normally ask IT support to handle. One firm rule: do this on your own machine, never the company laptop (an agent changing IT-managed settings is not your call to make), and have it explain what it wants to change before you approve

Claude Code vs. Antigravity

Both are agentic tools, but they feel different. Claude Code is more flexible, which matters for complex engineering. Antigravity is more visual and approachable, and since 2.0 the experience gap has narrowed a lot. The free tier makes it easy to add to your toolkit, though its weekly rate limits are low. Google AI Pro and Ultra come with higher limits and AI credits.

Who should use Antigravity

Developers and non-developers who want a visual, agent-powered environment for building web projects, games, and browser extensions — or for letting an agent work directly on their computer. A great complement to Claude Code for projects where speed and volume matter more than frontier reasoning.