jev-msw
Mock Jev API decisions with MSW for deterministic tests without real API calls.
OPEN SOURCE · CURATED REPOSITORIES
Curated Jev SDKs, tools, demos, integrations, benchmarks, and research projects. Repository metrics come from GitHub; titles, summaries, and categories are editorial.
Ranked by GitHub Stars
Ranked by recent Star growth and update activity
Mock Jev API decisions with MSW for deterministic tests without real API calls.
Semantic test matchers for Vitest and Jest that use TypeSafe's Jev model to evaluate plain-English expectations, returning calibrated probabilities and enabling deterministic CI replay.
CLI/GitHub Action that uses TypeSafe Jev/System One to explore web apps and find missing features, validation gaps, and dead controls before QA.
Open-source toolkit that uses TypeSafe Jev for gated evals, a browser loop, product walks, UI text judging, and first-click tests. Includes runnable scripts, an agent skill, and measured results.
Scores every test against a git diff with TypeSafe's Jev/System One model and emits filter arguments for vitest, node:test, Playwright, cargo test, and go test.
Convoy is an open-source semantic end-to-end testing tool for iOS, Android, and web. It calls TypeSafe AI's Jev model to match natural-language steps to UI controls, replacing selectors and element IDs.
A natural-language web E2E testing tool using Jev and playwright-cli. Jev makes decisions, Playwright executes browser actions, and code handles assertions and safety boundaries, with real TypeSafe API integration.
Automated friction logs for online documentation, scored section by section with TypeSafe Jev, with CI gating and dead-link checks.
Replay changed DecisionPacks over historical data, reuse judgments, and measure decision flips, with support for calling the TypeSafe Jev/System One API.
A CLI tool to test Agent Skills and docs across different agents in sandboxes, with optional TypeSafe Jev/System One grading integration.
semantic-assert is a TypeScript testing library that uses Jev, TypeSafe's first System One model, as a judge for plain-English assertions about captured page state. It ships a semantic-assert-typesafe provider package plus Playwright and Vercel AI SDK adapters that reach Jev directly or via Vercel AI Gateway.