{
  "aliases": [],
  "authors": [],
  "details": {
    "benchmark_protocol": {
      "actions": [
        "web browsing",
        "code execution",
        "coworker communication"
      ],
      "counts": [
        {
          "basis": "reported",
          "evidence_url": "https://raw.githubusercontent.com/TheAgentCompany/TheAgentCompany/HEAD/README.md",
          "population": "workspace images documented by the README",
          "qualifier": "exact",
          "unit": "task images",
          "value": 175
        }
      ],
      "evaluation": "Task-specific evaluator scripts run within the prepared workplace environment.",
      "evidence_urls": [
        "https://raw.githubusercontent.com/TheAgentCompany/TheAgentCompany/HEAD/README.md"
      ],
      "focus": [
        "professional workflows",
        "multi-tool tasks"
      ],
      "notes": "Each task is packaged as a Docker image. Record task-image and server versions; the environment includes simulated coworkers and external application state.",
      "observations": [],
      "setting": "interactive"
    },
    "leaderboard_url": "https://the-agent-company.com/#/leaderboard"
  },
  "environments": [
    "web",
    "desktop"
  ],
  "evidence": [
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-16T10:42:34Z",
      "role": "primary",
      "sha256": "d1646f67d49d38ef1e81bf7b5057dfc3d6f172b4c8a7413a2cc78741ccb08723",
      "supports": [
        "name",
        "kind",
        "summary",
        "environments",
        "topics",
        "scope",
        "relations",
        "details.benchmark_protocol",
        "details.leaderboard_url"
      ],
      "url": "https://raw.githubusercontent.com/TheAgentCompany/TheAgentCompany/HEAD/README.md"
    },
    {
      "method": "license_header",
      "retrieved_at": "2026-10-16T10:48:42Z",
      "role": "primary",
      "sha256": "2d6976a9b482bb14d9cd4f0d97ce6e14305496f1649b8667cb91d027c670930f",
      "supports": [
        "licenses.code"
      ],
      "url": "https://raw.githubusercontent.com/TheAgentCompany/TheAgentCompany/HEAD/LICENSE"
    }
  ],
  "id": "github:theagentcompany/theagentcompany",
  "identifiers": {},
  "kind": "benchmark",
  "last_verified_at": "2026-10-16T10:42:34Z",
  "licenses": {
    "code": {
      "basis": "repository LICENSE header; not a weights/data license",
      "declared": "MIT",
      "retrieved_at": "2026-10-16T10:48:42Z",
      "url": "https://raw.githubusercontent.com/TheAgentCompany/TheAgentCompany/HEAD/LICENSE"
    },
    "data": null,
    "document": null,
    "weights": null
  },
  "links": [
    {
      "rel": "primary",
      "url": "https://github.com/TheAgentCompany/TheAgentCompany"
    }
  ],
  "name": "TheAgentCompany",
  "notes": "",
  "published_at": null,
  "relations": [
    {
      "evidence_url": "https://raw.githubusercontent.com/TheAgentCompany/TheAgentCompany/HEAD/README.md",
      "target_id": "arxiv:2412.14161",
      "type": "documented_by"
    }
  ],
  "review_status": "curated",
  "scope": "core",
  "summary": "Self-contained workplace environment for evaluating agents on professional tasks involving websites, files, code, and simulated coworkers.",
  "topics": [
    "evaluation",
    "workflow",
    "cross-app"
  ],
  "updated_at": null,
  "url": "https://github.com/TheAgentCompany/TheAgentCompany"
}