competitor-meta.json

{
  "fetched_utc": "2026-09-09T10:16:15+00:00",
  "tool": "gh api (authenticated)",
  "repos": {
    "SWE-bench/SWE-bench": {
      "repo": "SWE-bench/SWE-bench",
      "license_spdx": "MIT",
      "stars": 5807,
      "pushed_at": "2026-09-02T01:51:01Z",
      "archived": false,
      "description": "SWE-bench: Can Language Models Resolve Real-world Github Issues?",
      "latest_release": null
    },
    "microsoft/SWE-bench-Live": {
      "repo": "microsoft/SWE-bench-Live",
      "license_spdx": "MIT",
      "stars": 234,
      "pushed_at": "2026-09-07T23:24:48Z",
      "archived": false,
      "description": "[NeurIPS 2025 D&B] \ud83d\ude80 SWE-bench Goes Live!",
      "latest_release": {
        "tag": "v1.0-multi-language-multi-os-benchmarking",
        "published_at": "2026-03-08T11:23:25Z"
      }
    },
    "sierra-research/tau-bench": {
      "repo": "sierra-research/tau-bench",
      "license_spdx": "MIT",
      "stars": 1427,
      "pushed_at": "2026-03-18T17:36:06Z",
      "archived": false,
      "description": "Code and Data for Tau-Bench",
      "latest_release": null
    },
    "sierra-research/tau2-bench": {
      "repo": "sierra-research/tau2-bench",
      "license_spdx": "MIT",
      "stars": 1991,
      "pushed_at": "2026-09-07T23:46:37Z",
      "archived": false,
      "description": "\u03c4-Bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains",
      "latest_release": {
        "tag": "v1.0.1",
        "published_at": "2026-07-22T21:22:42Z"
      }
    },
    "THUDM/AgentBench": {
      "repo": "THUDM/AgentBench",
      "license_spdx": "Apache-2.0",
      "stars": 3717,
      "pushed_at": "2026-02-08T17:01:05Z",
      "archived": false,
      "description": "A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)",
      "latest_release": null
    },
    "xlang-ai/OSWorld": {
      "repo": "xlang-ai/OSWorld",
      "license_spdx": "Apache-2.0",
      "stars": 3134,
      "pushed_at": "2026-08-30T09:41:51Z",
      "archived": false,
      "description": "[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments",
      "latest_release": {
        "tag": "v0.1.16",
        "published_at": "2024-06-26T04:22:29Z"
      }
    },
    "web-arena-x/webarena": {
      "repo": "web-arena-x/webarena",
      "license_spdx": "Apache-2.0",
      "stars": 1606,
      "pushed_at": "2025-11-26T21:16:00Z",
      "archived": false,
      "description": "Code repo for \"WebArena: A Realistic Web Environment for Building Autonomous Agents\"",
      "latest_release": {
        "tag": "v0.2.0",
        "published_at": "2023-10-21T04:35:19Z"
      }
    },
    "browser-use/browser-use": {
      "repo": "browser-use/browser-use",
      "license_spdx": "MIT",
      "stars": 113853,
      "pushed_at": "2026-09-07T19:55:36Z",
      "archived": false,
      "description": "Agents that use the browser.",
      "latest_release": {
        "tag": "0.13.10",
        "published_at": "2026-09-04T03:28:53Z"
      }
    },
    "UKGovernmentBEIS/inspect_ai": {
      "repo": "UKGovernmentBEIS/inspect_ai",
      "license_spdx": "MIT",
      "stars": 2734,
      "pushed_at": "2026-09-09T09:02:44Z",
      "archived": false,
      "description": "Inspect: A framework for large language model evaluations",
      "latest_release": null
    },
    "promptfoo/promptfoo": {
      "repo": "promptfoo/promptfoo",
      "license_spdx": "MIT",
      "stars": 24964,
      "pushed_at": "2026-09-09T09:43:10Z",
      "archived": false,
      "description": "Test your prompts, agents, and RAGs. Red teaming/pentesting/vulnerability scanning for AI. Compare performance of GPT, Claude, Gemini, DeepSeek, and more. Simple declarative configs with command line and CI/CD integration.  Used by OpenAI and Anthropic.",
      "latest_release": {
        "tag": "code-scan-action-0.2.0",
        "published_at": "2026-08-28T07:34:11Z"
      }
    },
    "confident-ai/deepeval": {
      "repo": "confident-ai/deepeval",
      "license_spdx": "Apache-2.0",
      "stars": 18186,
      "pushed_at": "2026-09-08T07:08:59Z",
      "archived": false,
      "description": "The LLM Evaluation Framework",
      "latest_release": {
        "tag": "python-v4.2.0",
        "published_at": "2026-08-24T21:56:54Z"
      }
    },
    "AgentOps-AI/agentops": {
      "repo": "AgentOps-AI/agentops",
      "license_spdx": "MIT",
      "stars": 5813,
      "pushed_at": "2026-06-25T08:25:03Z",
      "archived": false,
      "description": "Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI",
      "latest_release": {
        "tag": "0.4.21",
        "published_at": "2025-08-29T06:36:28Z"
      }
    },
    "Arize-ai/phoenix": {
      "repo": "Arize-ai/phoenix",
      "license_spdx": "NOASSERTION",
      "stars": 11388,
      "pushed_at": "2026-09-09T05:22:55Z",
      "archived": false,
      "description": "AI Observability & Evaluation",
      "latest_release": {
        "tag": "arize-phoenix-client-v3.5.0",
        "published_at": "2026-09-08T22:22:38Z"
      }
    },
    "langfuse/langfuse": {
      "repo": "langfuse/langfuse",
      "license_spdx": "NOASSERTION",
      "stars": 34392,
      "pushed_at": "2026-09-09T10:06:57Z",
      "archived": false,
      "description": "\ud83e\udea2 Open source AI engineering platform: LLM evals, observability, metrics, prompt management, playground, datasets. Integrates with OpenTelemetry, LangChain, OpenAI SDK, LiteLLM, and more. \ud83c\udf4aYC W23 ",
      "latest_release": {
        "tag": "v4.32.0",
        "published_at": "2026-09-08T12:53:51Z"
      }
    },
    "openai/evals": {
      "repo": "openai/evals",
      "license_spdx": "NOASSERTION",
      "stars": 19414,
      "pushed_at": "2026-04-14T15:29:57Z",
      "archived": false,
      "description": "Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.",
      "latest_release": null
    }
  }
}