Designers and developers wanting quick first drafts of app screens; free as a Google Labs experiment, which means limits and no guarantees.
Kenning's take
What it does
Stitch is a Google Labs tool that creates mobile and web interface designs from a written description, a screenshot or a rough wireframe. Users can generate several versions, refine them in a chat, paste the result into Figma or export front-end code. It runs in the browser at stitch.withgoogle.com, and there is an extension for Gemini CLI that talks to Stitch's MCP server.
- Generate UI from plain-English prompts
- Generate UI from images or wireframes
- Multiple design variants
- Paste to Figma
- Export front-end code
- Gemini CLI extension and MCP server
Who it suits. Designers and developers who want quick first drafts of app and website screens.
Key facts
- Category
- Developer tools
- Made by
- Based in
- United States
- Released
- 20 May 2025
- How to get it
- free in the browser at stitch.withgoogle.com with a Google account; it is a Google Labs experiment
- Works on
- Web, Gemini CLI extension
- Free plan
- Free with daily credit limits (reported by Banani's April 2026 review; Google's own FAQ could not be read)
Reviews and write-ups
- Banani 2026-04-20
FAQ
When was Google Stitch released?
Google announced Stitch on 20 May 2025 at Google I/O.
Is Google Stitch free?
Yes, it is free while it is a Google Labs experiment, with daily usage limits.
Can Stitch export to Figma?
Yes. Designs can be pasted into Figma, and front-end code can be exported.
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OpenAI's visual canvas for building multi-agent workflows, being withdrawn on 30 November 2026.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.