agentos-bench/package.json at master · framerslab/agentos-bench · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
{
  "name": "@framers/agentos-bench",
  "version": "0.2.0",
  "description": "Benchmark suite for AgentOS memory — LongMemEval, LOCOMO, BEAM, and cognitive-mechanism micro-benchmarks. Includes per-category reader router calibration, vendor reproduction adapters, and full transparency stack (per-cell run JSONs, bootstrap CIs, judge FPR probes, negative findings).",
  "type": "module",
  "main": "./dist/index.js",
  "types": "./dist/index.d.ts",
  "exports": {
    ".": {
      "import": "./dist/index.js",
      "types": "./dist/index.d.ts"
    },
    "./core": {
      "import": "./dist/core/index.js",
      "types": "./dist/core/index.d.ts"
    },
    "./benchmarks/*": {
      "import": "./dist/benchmarks/*/index.js",
      "types": "./dist/benchmarks/*/index.d.ts"
    },
    "./micro/*": {
      "import": "./dist/micro/*.js",
      "types": "./dist/micro/*.d.ts"
    }
  },
  "bin": {
    "agentos-bench": "./dist/cli.js"
  },
  "files": [
    "dist",
    "src",
    "results/LEADERBOARD.md",
    "results/summary.json"
  ],
  "scripts": {
    "build": "tsc -p tsconfig.json",
    "test": "vitest run",
    "test:watch": "vitest",
    "typecheck": "tsc --noEmit",
    "bench": "node ./dist/cli.js",
    "leaderboard": "node ./dist/cli.js leaderboard",
    "setup": "node ./dist/cli.js setup",
    "clean": "rimraf dist"
  },
  "peerDependencies": {
    "@framers/agentos": "^0.6.6"
  },
  "dependencies": {
    "commander": "^12.0.0",
    "csv-parse": "^5.5.0",
    "stream-chain": "^3.6.1",
    "stream-json": "^2.1.0",
    "zod": "^4.3.6"
  },
  "optionalDependencies": {
    "@huggingface/hub": "^1.0.0"
  },
  "devDependencies": {
    "@framers/agentos": "^0.6.6",
    "@types/node": "^20.12.12",
    "@types/stream-json": "^1.7.8",
    "better-sqlite3": "^12.9.0",
    "rimraf": "^5.0.7",
    "typescript": "^5.5.0",
    "vitest": "^1.6.0"
  },
  "license": "Apache-2.0",
  "author": "Frame.dev",
  "repository": {
    "type": "git",
    "url": "https://github.com/framersai/agentos-bench.git"
  },
  "homepage": "https://docs.agentos.sh/benchmarks",
  "bugs": {
    "url": "https://github.com/framersai/agentos-bench/issues"
  },
  "publishConfig": {
    "access": "public"
  },
  "keywords": [
    "agentos",
    "framers-agentos",
    "agentos-bench",
    "benchmark",
    "ai-agent-benchmark",
    "memory",
    "memory-benchmark",
    "ai-memory",
    "cognitive-memory",
    "longmemeval",
    "locomo",
    "beam",
    "eval",
    "evaluation",
    "ai-evaluation",
    "llm-benchmark",
    "framers",
    "frame-dev"
  ]
}