jevcumber

Write Cucumber tests with just the .feature file. No step definitions — Jev (TypeSafe AI) resolves each Gherkin step and Playwright runs it.

How it uses Jev

jevcumber opens your site in a real browser with Playwright and, for each Gherkin step, asks Jev — TypeSafe AI's fast System One model — what the step means on the page in front of it .

Use cases

  • uses: actions/setup-node@v4
  • run: npm install -g jevcumber
  • run: jevcumber install-browser --with-deps
  • run: jevcumber features/ --frozen --base-url http://localhost:3000
  • run: jevcumber explain features/ optional: prints what every step resolves to, for the PR log

Source: community catalog. Details and metrics reflect the published community snapshot and are not a performance endorsement. Documentation details extracted from GitHub · the README · the project website.

Keep exploring

Similar to jevcumber

Browse all
jev-test-filter project preview
Browser & computer use
Score every test against a git diff with Jev, and emit the filter arguments vitest, node:test, Playwright, cargo test and go test already understand
jev-browser (vinilana) project preview
Browser & computer use
Hybrid browser harness: an LLM turns goals into verifiable subgoals, Jev chooses each action and DOM field, Playwright acts.
jev-browser (openqa-cn) project preview
Browser & computer use
Jev Browser — indexed browser automation. Jev chooses the control, Playwright acts. A CodexQA skill.
bicameral project preview
Agent tooling
Hybrid coding harness: System 2 writes, System 1 (Jev) runs reflexes.
jev-flash-router project preview
Benchmarks & research
open-sourced jev-flash-router: an MCP server for TypeSafe's new Jev model. AI coding agents waste hundreds of reasoning tokens just deciding which file to edit, which route to pick, or whether a diff breaks tests. Jev evaluates state and outputs calibrated probabilities. Works with Cursor, Windsurf, & Claude Code
pijev project preview
Agent tooling
PiJev: a terminal coding agent with Jev in the loop — Jev ranks the repository's files before the first call, picks skills and triages failures; your coding model writes the code. Built on Pi.
jev-ui project preview
Benchmarks & research
React components that resolve which component to render, how to order a list, and whether to show an affordance — from calibrated judgments returned by TypeSafe's Jev.
jev-skillful project preview
Agent tooling
Per-prompt capability router for coding agents: resolves installed skills, MCP servers, agents and commands against your prompt via TypeSafe Jev, and measures whether the injection actually helps.
notra project preview
Applications
Marketing analytics platform whose feature flag routes brand-visibility classifiers off an LLM and onto Jev boolean decisions.