Jev in production › Evaluation and testing
playwright-jev (AdriaanVE)
Jev powers failure triage, automatic retries, locator healing and semantic assertions as Playwright reporter and test plugins.
The source publishes no measured number.
- Use
- Evaluation and testing
- Industry
- Developer tools
- Form
- Open-source tool
- Stage
- Beta
- Plugs into
- Playwright
- Listed
- 2026-10-01
- Found via
- github
- Repository
- AdriaanVE/playwright-jev
- Stars
- 2
- Forks
- 0
- Last push
- 2026-09-29
- Language
- TypeScript
- License
- MIT
The README opens with
Structured decisions for Playwright. playwright-jev sends small typed questions to a decision model, by default JEV on OpenRouter or TypeSafe's own JEV API, at points where a test suite or a Playwright agent would otherwise rerun everything, wait on a human, or spend a full LLM turn.
It is an add-on to @playwright/test, not a fork. You keep running npx playwright test. Each feature plugs into an extension point Playwright already has, and you can adopt them one at a time:
Badge
For the project's own README, linking back here:
Also used for evaluation and testing
- jevals (Openlayer) p50 244ms
- grounded-ai (CascadeEvaluator) 51% faster
- Pinecone Cultivar ~30x cheaper
- jev-test-filter $0.00098
- Jev Arena 7,671
- touchpress 29 seconds
- SmartMoney-Cub 78.43%
- MetaCog 86.7 %