# abi/screenshot-to-code

Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)

Repository: https://github.com/abi/screenshot-to-code
Canonical: https://ross.abutalabs.com/products/screenshot-to-code
Homepage: https://screenshottocode.com
Language: Python
License: MIT
License Family: permissive
Last push: 2026-08-14T17:20:50+00:00

## Health v2 (maintenance only)
Score: 70/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 97, release rhythm 35, longevity 73
- inputs: {"age_days": 1023, "days_push": 19, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 74677, forks 9144 (observed 2026-08-28T04:12:21.477073+00:00)

## What it is
An AI-powered application that converts screenshots, mockups, Figma designs, and screen recordings into clean functional code (HTML/Tailwind, React, Vue, Bootstrap, Ionic). It ships as a React/Vite frontend with a FastAPI backend that calls LLM providers like Gemini, OpenAI, and Anthropic.

## Use cases
- convert a screenshot of a webpage into HTML and Tailwind code
- turn a Figma design into a React component
- generate a Vue page from a UI mockup
- recreate a landing page from an image
- turn a screen recording of a website into a working prototype
- bootstrap frontend code from a design handoff

## When to choose
- you want to quickly scaffold frontend code from a visual design or screenshot
- you need a starting point for recreating an existing UI in HTML/Tailwind, React, or Vue
- you want a self-hostable AI design-to-code tool with multiple model provider options

## When to avoid
- you need pixel-perfect, production-ready code without manual cleanup
- you cannot provide API keys for cloud LLM providers and require fully offline generation
- you are converting complex application logic rather than visual UI

## Facets
- artifact type: application
- maturity: active
- function: machine-learning, llm-inference, web-framework, frontend-framework
- domain: web-development, artificial-intelligence, large-language-models, developer-tools
- platform: self-hosted, python
- tags: screenshot-to-code, design-to-code, tailwind, react, vue, figma, ai-codegen, fastapi, code-generation, web-server, docker, nodejs

## Member repositories
- abi/screenshot-to-code (main) score 70

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:12:21.477073+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:14:48.221453+00:00, confidence not recorded.
  - readme: https://github.com/abi/screenshot-to-code (fetched 2026-08-28T04:12:21.477073+00:00, sha 254afacb5908)
  - homepage: https://screenshottocode.com (fetched 2026-08-28T17:45:51.902939+00:00, sha c95e3292193e)
- Data as of 2026-08-30T08:39:29.467469+00:00.