Quick Gemini-powered prototypes, web or Android, for free in the browser; API costs arrive once deployed apps get real use.
Kenning's take
What it does
Build mode in Google AI Studio lets users describe an app in plain language and get a working full-stack web app or native Android app with a live preview. It runs on the Antigravity agent, which manages files across the project, installs npm packages and keeps secrets on the server side. Projects can be started from a prompt, remixed from a gallery or imported from GitHub.
- Full-stack web apps with React and Node.js
- Native Android apps in Kotlin and Jetpack Compose
- Powered by the Antigravity agent
- Import from GitHub or remix gallery apps
- Server-side secrets and npm packages
Who it suits. People who want to prototype Gemini-powered apps quickly, with or without much coding.
Key facts
- Category
- Developer tools
- Part of
- Google AI Studio
- Made by
- Based in
- United States
- How to get it
- Inside Google AI Studio in the browser with a Google account
- Works on
- Web
- In the UK
- Yes
- Free plan
- Free to use in Google AI Studio
FAQ
What can Google AI Studio Build mode make?
Full-stack web apps and native Android apps, generated from a text prompt.
How do I use Build mode?
Open Build mode in Google AI Studio and describe the app, or import a project from GitHub.
Facts from the maker's own pages and the sources listed. Checked 2026-10-11.
Similar tools
Claude Keychain
A free Mac menu bar app that keeps API keys in the macOS Keychain so Claude Code can use them without seeing them.
OpenAI Agent Builder
OpenAI's visual canvas for building multi-agent workflows, being withdrawn on 30 November 2026.
ElevenLabs Agent Workflows
Visual editor in ElevenLabs' agent platform for designing branching conversation flows for voice and chat agents.
AgentOps
Monitoring and debugging platform that records what AI agents do, what they cost and where they fail.