Jev in production › Agent tool and action selection
jev-playwright (cooper667)
Jev selects page elements and judges pass or fail checks for plain-English browser QA steps; vendor claims 24 steps run in 35 seconds versus 14 minutes manually (author).
35smeasured against a baseline, as published by the source
- Use
- Agent tool and action selection
- Industry
- Developer tools
- Form
- Open-source tool
- Stage
- In production
- Plugs into
- Playwright
- Listed
- 2026-10-01
- Found via
- github
- Repository
- cooper667/jev-playwright
- Stars
- 7
- Forks
- 1
- Last push
- 2026-10-09
- Language
- TypeScript
- License
- MIT
The README opens with
Runs a checklist written in plain English, one action or check per line, in a real browser. Playwright drives the page and a classifier decides each step: which element an action means, and whether a check holds. An agent uses it to check its own work after a user-visible change, to run a pull request's QA steps as written, or to compare two builds. It starts from any URL, or logged in through an app's own e2e fixture. A 24-step flow takes about 35 seconds.
Badge
For the project's own README, linking back here:
Also used for agent tool and action selection
- typesafe-computer-use $0.0002
- EZCollegeApp (via jev-browser-use) ~5–10×
- system1-agents 25× cheaper
- jev-use (savka777) about 0.3–1.5 s per step
- fastbrowse 41/42
- Jev GUI Delegate 89.6-91.5%
- QuickE2E 3.74s
- jev-ui-test 458ms