#2121st of 22 in Code review and testing
shortest
Write end-to-end browser tests in plain English, executed by Claude via Playwright
- Stars
- 5.7k
- License
- MIT
- Last commit
- May 2026
- Last release
- Apr 2025
- Language
- TypeScript
5,521 on 10 Apr 20265,700 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Shortest is a TypeScript test framework where each test is a natural-language sentence. Claude, called through the Anthropic API, drives a Playwright browser to carry it out. It supports `.after()` callbacks for custom assertions, lifecycle hooks, chained tests, API endpoint tests, GitHub 2FA login and Mailosaur email checks.
Who it is for: Web teams wanting AI-driven E2E tests on top of Playwright
Strengths
- Tests are plain-English strings; `.after()` callbacks allow Playwright and DB assertions in code
- Built on Playwright, with browser context options passed through the config file
- Headless mode for CI, with an example GitHub Actions workflow in the repo
- Built-in GitHub 2FA (TOTP) login and Mailosaur email validation
Weaknesses
- Only the Anthropic provider is documented; an API key is required and each run costs tokens
- Last tagged release is 2025-04-01
- AI-executed steps can be non-deterministic and slower than scripted Playwright tests
- Repo also contains a web app that needs Clerk, Postgres, Stripe and Mailosaur to run locally
What it needs
- no GPU
- Needs Anthropic API, Playwright, Mailosaur (optional), Clerk, Vercel Postgres, Stripe (web app only)
- Models: Anthropic Claude
- port 3000
Quick answers
Is shortest open source?
Yes. Its code is on GitHub under the MIT license.
Also in Code review and testing
See all 22| Rank | Project | Score |
|---|---|---|
| 1 | playwrightCross-browser automation and end-to-end test framework for Chromium, Firefox and WebKit | 94 out of 100 |
| 2 | open-code-reviewCLI that reviews Git diffs with an LLM agent and line-level comments | 91 out of 100 |
| 3 | react-doctorCLI that scans React codebases for state, performance, security and accessibility issues | 89 out of 100 |
| #4 | pr-agentLLM pull request reviewer that comments via /review, /describe and /improve | 86 out of 100 |
| #5 | e2eAI-driven end-to-end testing framework for web and mobile apps | 86 out of 100 |