Jev Ci

An open-source merge gateway for repositories where agents write most commits: a System One model answers five fixed questions per pull request with calibrated probabilities in roughly 300 ms, a YAML policy turns them into pass, hold or block, and a planner lands non-conflicting PRs in waves.

A Playwright reporter that uses Jev to score which existing E2E tests a code change could affect and runs only those above a confidence threshold before browser execution, failing open to the full suite.

Local-first test selector that asks a judge — classifier.dev by default, or Jev with a TypeSafe key — whether each test could be affected by the current code change, then hands only the selected files to Playwright or Vitest. Uncertainty always runs the full suite.

pytest-style behavioral contracts for Jev: pin a production contract of baseline model plus fixtures, eval a candidate model against it, and fail the upgrade when answers flip or confidence regresses.

A GitHub Action that reviews repository files with your own yes/no questions: Jev returns probabilities and the check passes only when every expected answer meets its configured threshold.

A GitHub Action that treats .jev.yml as a semantic linter for pull requests: each rule is a typed Jev question (Noul, Choice or Score) and the check fails, comments or passes from those numbers. It writes no reviews, suggests no patches and approves nothing.

A testing app and CLI for chat endpoints: send messages to any chat API, watch replies stream in as a conversation, and check every reply with rule checks (JSONPath, latency, tokens, cost, tool calls) and judged checks including TypeSafe's System One. Export the suites as files and run them in CI.

A stateless Rust CLI for typed semantic judgments with the Jev model: state and questions in, calibrated answers and exit codes out, as stable JSON on stdout. Ships with an Agent Skill for scripts, CI and agent workflows.