jev-evals/package.json

Rubric-based eval harness for LLM/agent outputs, backed by the typesafe-ai/jev evaluation model via Vercel AI Gateway. Cheap enough (~$0.04/1M input tokens, one round trip per case) to run on every PR.

{
  "name": "jev-evals",
  "version": "0.1.0",
  "description": "Rubric-based eval harness for LLM/agent outputs, backed by the typesafe-ai/jev evaluation model via Vercel AI Gateway. Cheap enough (~$0.04/1M input tokens, one round trip per case) to run on every PR.",
  "type": "module",
  "main": "./dist/index.js",
  "module": "./dist/index.js",
  "types": "./dist/index.d.ts",
  "exports": {
    ".": {
      "types": "./dist/index.d.ts",
      "import": "./dist/index.js"
    },
    "./package.json": "./package.json"
  },
  "bin": {
    "jev-evals": "dist/cli.js"
  },
  "files": [
    "dist",
    "README.md"
  ],
  "scripts": {
    "build": "tsup",
    "dev": "tsup --watch",
    "typecheck": "tsc --noEmit",
    "test": "vitest run",
    "test:watch": "vitest",
    "prepublishOnly": "npm run typecheck && npm run test && npm run build"
  },
  "keywords": [
    "eval",
    "evals",
    "llm",
    "llm-as-judge",
    "rubric",
    "jev",
    "ai-sdk",
    "ci",
    "agent"
  ],
  "license": "MIT",
  "peerDependencies": {
    "ai": "^7.0.105"
  },
  "devDependencies": {
    "ai": "^7.0.105",
    "tsup": "^8.3.5",
    "typescript": "^5.7.2",
    "vitest": "^2.1.8",
    "@types/node": "^22.10.2"
  },
  "engines": {
    "node": ">=18.17"
  }
}