{
  "id": "the-agent-company",
  "name": "TheAgentCompany",
  "category": "information",
  "summary": "Benchmark of 175 professional tasks in a simulated software company (self-hosted GitLab, Plane, ownCloud, RocketChat) for agents that browse, code, run programs and talk to coworkers.",
  "description": "Self-hosted with Docker (30+ GB disk); each task is a Docker image with an encrypted evaluator. Scoring is result-based (primary) plus subcheckpoints (secondary), using deterministic and LLM-based evaluators; tasks include communicating with coworkers (an `npc` component in each task image). Task roles: software engineer, product manager, data scientist, human resources, financial staff and administrator. Paper: arXiv 2412.14161; maintainers' contacts are at CMU. Public leaderboard on the website. Release 1.0.0 (December 2024).",
  "url": "https://the-agent-company.com",
  "repo": "https://github.com/TheAgentCompany/TheAgentCompany",
  "tags": [
    "benchmark",
    "agents",
    "workplace-tasks",
    "web-agents",
    "evals"
  ],
  "license": "MIT",
  "pricing": "free",
  "status": "active",
  "related": [
    "webarena",
    "appworld",
    "osworld",
    "openhands"
  ],
  "sources": [
    "https://github.com/TheAgentCompany/TheAgentCompany",
    "https://arxiv.org/abs/2412.14161",
    "https://the-agent-company.com"
  ],
  "added": "2026-10-26",
  "updated": "2026-10-26",
  "last_verified": "2026-10-26",
  "submitted_by": "agentica-curator",
  "maintainer": "TheAgentCompany",
  "longform": [],
  "links": {
    "html": "https://indexagentica.com/entries/the-agent-company/",
    "markdown": "https://indexagentica.com/entries/the-agent-company.md",
    "json": "https://indexagentica.com/api/entries/the-agent-company.json",
    "source": "https://github.com/Drudley/indexagentica/blob/main/content/information/the-agent-company.json"
  }
}