# antiwork/shortest

QA via natural language AI tests

Repository: https://github.com/antiwork/shortest
Canonical: https://ross.abutalabs.com/products/shortest
Homepage: https://shortest.com
Language: TypeScript
License: MIT
License Family: permissive
Topics: anthropic, automation, chromium, e2e-testing, e2e-tests, end-to-end-testing, javascript, nextjs, playwright, test-automation, testing, testing-framework, testing-tool
Last push: 2026-08-06T15:23:13+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 96, release rhythm 40, longevity 51
- inputs: {"age_days": 714, "days_push": 27, "days_rel": 520, "gap_med": 6, "n_releases_24m": 12}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5667, forks 338 (observed 2026-08-28T04:09:27.595382+00:00)

## What it is
Shortest is an AI-powered end-to-end testing framework that lets developers write browser tests in plain English, executed via Anthropic's Claude API on top of Playwright. It includes GitHub integration with 2FA support and email validation via Mailosaur.

## Use cases
- write e2e tests in natural language
- automate login flow testing with AI
- test web apps without writing selectors
- run AI-driven browser QA checks
- validate email flows during end-to-end tests
- test GitHub sign-in including 2FA

## When to choose
- you want plain-English E2E tests instead of brittle selectors
- your stack is TypeScript/Next.js and already uses Playwright
- you need AI to handle test implementation from scenario descriptions

## When to avoid
- you need fully deterministic, fast CI tests without LLM costs or flakiness
- you don't want to send app context to an external AI API
- you need non-browser or API-only testing

## Facets
- artifact type: framework
- maturity: active
- function: e2e-testing, testing, agent-framework, llm-inference
- domain: testing, web-development, artificial-intelligence, developer-tools
- platform: cross-platform, cli
- tags: natural-language-testing, playwright, anthropic-claude, test-automation, qa, browser-testing, nodejs

## Member repositories
- antiwork/shortest (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:27.595382+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 2026-08-29T17:54:18.678860+00:00, confidence not recorded.
  - readme: https://github.com/antiwork/shortest (fetched 2026-08-28T04:09:27.595382+00:00, sha ef4a9c29843a)
  - homepage: https://shortest.com (fetched 2026-08-29T08:49:46.493132+00:00, sha 0d8ebdcc5a42)
- Data as of 2026-08-30T08:39:29.467469+00:00.