{
  "project": {
    "project_id": "agentevals-dev/agentevals",
    "repo": "agentevals-dev/agentevals",
    "name": "agentevals",
    "github_url": "https://github.com/agentevals-dev/agentevals",
    "homepage_url": "https://aevals.ai/",
    "language": "Python",
    "license": "Apache-2.0",
    "project_kind": "project",
    "category": [
      "llm_eval"
    ],
    "tags": [
      "agentevals",
      "agents",
      "evals",
      "evaluation",
      "genai",
      "llm",
      "llm-as-judge",
      "opentelemetry",
      "otel",
      "tracing"
    ],
    "description": "agentevals is a framework-agnostic evaluations solution based on OpenTelemetry traces",
    "overview": "Use agentevals-dev/agentevals when the user needs a llm eval project with docker, kubernetes, library-only deployment options.",
    "alternatives": [
      {
        "repo": "comet-ml/opik",
        "reason": "Same llm eval intent with observability overlap."
      },
      {
        "repo": "Arize-ai/phoenix",
        "reason": "Same llm eval intent with observability overlap."
      },
      {
        "repo": "lmnr-ai/lmnr",
        "reason": "Same llm eval intent with observability overlap."
      }
    ],
    "related": [],
    "dependencies": [
      "LLM provider"
    ],
    "deployments": [
      "docker",
      "kubernetes",
      "library_only",
      "local",
      "cloud"
    ],
    "difficulty": "beginner",
    "cloudflare_ready": false,
    "use_cases": [
      "evaluate LLM outputs",
      "benchmark prompts and agents",
      "track model quality"
    ],
    "not_good_for": [
      "edge-only Cloudflare Workers deployment without adaptation",
      "users expecting a complete hosted product"
    ],
    "classification": {
      "category": {
        "confidence": "high",
        "evidence": [
          "Matched \"eval\" in metadata.",
          "Matched \"evaluation\" in metadata."
        ]
      },
      "deployment": {
        "confidence": "high",
        "evidence": [
          "Found Docker configuration file.",
          "Matched \"kubernetes\" in repository content.",
          "Matched \"helm chart\" in repository content.",
          "Matched \"pip install\" in repository content.",
          "Local usage is assumed for open source repositories unless contradicted."
        ]
      },
      "difficulty": {
        "confidence": "medium",
        "evidence": [
          "Repository has under 10k stars, so complexity is treated conservatively."
        ]
      },
      "cloudflare_ready": {
        "confidence": "high",
        "evidence": [
          "Runtime blocker: python, postgres.",
          "No Cloudflare deployment signal detected.",
          "No wrangler.toml found in inspected repository files."
        ]
      }
    },
    "quality_signals": {
      "stars": 162,
      "recent_commits": 26,
      "contributors": 17,
      "issue_response_time_hours": null,
      "release_frequency_180d": 25
    },
    "quality_signal_confidence": {
      "stars_30d_delta": "snapshot",
      "stars30d_window_days": 36,
      "commits_30d": "complete",
      "releases_180d": "complete",
      "contributors_90d": "complete"
    },
    "quality_score": 25,
    "agent_score": 69,
    "score": 86,
    "agent_score_breakdown": {
      "documentation": 90,
      "maintenance": 49,
      "deployment": 100,
      "popularity": 44,
      "community": 62
    },
    "git_top_score": 86,
    "git_top_score_breakdown": {
      "community": 100,
      "maintenance": 65,
      "documentation": 92,
      "stability": 100,
      "adoption": 63,
      "agent_readability": 100
    },
    "verification": {
      "schema_version": "git-top.verification.v1",
      "overall_status": "partial",
      "observed_at": "2026-09-22T20:01:00.470Z",
      "signals": {
        "activity": {
          "status": "observed",
          "source": "github_metadata",
          "evidence": [
            "project.pushed_at",
            "metrics.recent_push_days"
          ]
        },
        "license": {
          "status": "observed",
          "source": "github_metadata",
          "evidence": [
            "project.license"
          ]
        },
        "documentation": {
          "status": "observed",
          "source": "github_metadata",
          "evidence": [
            "project.description"
          ]
        },
        "runtime": {
          "status": "inferred",
          "source": "git_top_heuristic",
          "evidence": [
            "agent_card.deployment",
            "agent_card.cloudflare_ready"
          ]
        },
        "install": {
          "status": "not_run",
          "source": "git_top_runtime",
          "evidence": [
            "installation/build probe is not enabled"
          ]
        },
        "security": {
          "status": "not_run",
          "source": "git_top_runtime",
          "evidence": [
            "dependency/security scan is not enabled"
          ]
        },
        "mcp": {
          "status": "not_applicable",
          "source": "git_top_runtime",
          "evidence": [
            "project is not classified as mcp_server"
          ]
        }
      },
      "coverage": {
        "observed": 3,
        "inferred": 1,
        "not_run": 2,
        "unknown": 0
      },
      "next_steps": [
        "Run an installation/build probe before production adoption.",
        "Run a dependency and security scan before treating the score as a trust claim."
      ]
    },
    "summary": {
      "tl_dr": "Use agentevals-dev/agentevals when the user needs a llm eval project with docker, kubernetes, library-only deployment options.",
      "purpose": "Use agentevals-dev/agentevals when the user needs a llm eval project with docker, kubernetes, library-only deployment options.",
      "install": "Run with Docker using the repository's container instructions.",
      "inputs": [
        "prompts",
        "model outputs",
        "test cases"
      ],
      "outputs": [
        "scores",
        "benchmarks",
        "eval reports"
      ],
      "good_for": [
        "evaluate LLM outputs",
        "benchmark prompts and agents",
        "track model quality",
        "model evaluation",
        "benchmarking",
        "regression testing"
      ],
      "not_good_for": [
        "edge-only Cloudflare Workers deployment without adaptation",
        "users expecting a complete hosted product",
        "production inference serving",
        "end-user chat apps"
      ],
      "deployment": [
        "docker",
        "kubernetes",
        "library_only",
        "local",
        "cloud"
      ],
      "alternatives": [
        {
          "repo": "comet-ml/opik",
          "reason": "Same llm eval intent with observability overlap."
        },
        {
          "repo": "Arize-ai/phoenix",
          "reason": "Same llm eval intent with observability overlap."
        },
        {
          "repo": "lmnr-ai/lmnr",
          "reason": "Same llm eval intent with observability overlap."
        }
      ]
    },
    "evidence": {
      "classification": {
        "category": {
          "confidence": "high",
          "evidence": [
            "Matched \"eval\" in metadata.",
            "Matched \"evaluation\" in metadata."
          ]
        },
        "deployment": {
          "confidence": "high",
          "evidence": [
            "Found Docker configuration file.",
            "Matched \"kubernetes\" in repository content.",
            "Matched \"helm chart\" in repository content.",
            "Matched \"pip install\" in repository content.",
            "Local usage is assumed for open source repositories unless contradicted."
          ]
        },
        "difficulty": {
          "confidence": "medium",
          "evidence": [
            "Repository has under 10k stars, so complexity is treated conservatively."
          ]
        },
        "cloudflare_ready": {
          "confidence": "high",
          "evidence": [
            "Runtime blocker: python, postgres.",
            "No Cloudflare deployment signal detected.",
            "No wrangler.toml found in inspected repository files."
          ]
        }
      },
      "quality_signal_confidence": {
        "stars_30d_delta": "snapshot",
        "stars30d_window_days": 36,
        "commits_30d": "complete",
        "releases_180d": "complete",
        "contributors_90d": "complete"
      },
      "verification": {
        "schema_version": "git-top.verification.v1",
        "overall_status": "partial",
        "observed_at": "2026-09-22T20:01:00.470Z",
        "signals": {
          "activity": {
            "status": "observed",
            "source": "github_metadata",
            "evidence": [
              "project.pushed_at",
              "metrics.recent_push_days"
            ]
          },
          "license": {
            "status": "observed",
            "source": "github_metadata",
            "evidence": [
              "project.license"
            ]
          },
          "documentation": {
            "status": "observed",
            "source": "github_metadata",
            "evidence": [
              "project.description"
            ]
          },
          "runtime": {
            "status": "inferred",
            "source": "git_top_heuristic",
            "evidence": [
              "agent_card.deployment",
              "agent_card.cloudflare_ready"
            ]
          },
          "install": {
            "status": "not_run",
            "source": "git_top_runtime",
            "evidence": [
              "installation/build probe is not enabled"
            ]
          },
          "security": {
            "status": "not_run",
            "source": "git_top_runtime",
            "evidence": [
              "dependency/security scan is not enabled"
            ]
          },
          "mcp": {
            "status": "not_applicable",
            "source": "git_top_runtime",
            "evidence": [
              "project is not classified as mcp_server"
            ]
          }
        },
        "coverage": {
          "observed": 3,
          "inferred": 1,
          "not_run": 2,
          "unknown": 0
        },
        "next_steps": [
          "Run an installation/build probe before production adoption.",
          "Run a dependency and security scan before treating the score as a trust claim."
        ]
      },
      "source_fields": [
        "project.description",
        "project.topics",
        "project.language",
        "project.license",
        "agent_card.summary_for_agent",
        "agent_card.use_cases",
        "agent_card.deployment",
        "agent_card.classification",
        "metrics",
        "verification.signals"
      ],
      "caveats": [
        "edge-only Cloudflare Workers deployment without adaptation",
        "users expecting a complete hosted product",
        "Independent installation, security, or runtime probes have not been run for this project."
      ],
      "confidence_reason": "Classification evidence and quality signals are strong enough for shortlist reasoning when metadata is current.",
      "last_verified_at": "2026-09-22T20:01:00.470Z"
    },
    "caveats": [
      "edge-only Cloudflare Workers deployment without adaptation",
      "users expecting a complete hosted product",
      "Independent installation, security, or runtime probes have not been run for this project."
    ],
    "confidence_reason": "Classification evidence and quality signals are strong enough for shortlist reasoning when metadata is current.",
    "source_fields": [
      "project.description",
      "project.topics",
      "project.language",
      "project.license",
      "agent_card.summary_for_agent",
      "agent_card.use_cases",
      "agent_card.deployment",
      "agent_card.classification",
      "metrics",
      "verification.signals"
    ],
    "last_verified_at": "2026-09-22T20:01:00.470Z"
  },
  "related": [
    {
      "project_id": "promptfoo/promptfoo",
      "repo": "promptfoo/promptfoo",
      "name": "promptfoo",
      "github_url": "https://github.com/promptfoo/promptfoo",
      "homepage_url": "https://promptfoo.dev",
      "language": "TypeScript",
      "license": "MIT",
      "project_kind": "project",
      "category": [
        "llm_eval"
      ],
      "tags": [
        "ci",
        "ci-cd",
        "cicd",
        "evaluation",
        "evaluation-framework",
        "llm",
        "llm-eval",
        "llm-evaluation",
        "llm-evaluation-framework",
        "llmops",
        "pentesting",
        "prompt-engineering",
        "prompt-testing",
        "prompts",
        "rag",
        "red-teaming",
        "testing",
        "vulnerability-scanners"
      ],
      "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.",
      "overview": "Use promptfoo/promptfoo when the user needs a llm eval project with docker, library-only, local deployment options.",
      "alternatives": [
        {
          "repo": "comet-ml/opik",
          "reason": "Same llm eval intent with rag overlap."
        },
        {
          "repo": "Giskard-AI/giskard-oss",
          "reason": "Same llm eval intent with rag overlap."
        },
        {
          "repo": "promptfoo/promptfoo-action",
          "reason": "Same llm eval intent with rag overlap."
        }
      ],
      "related": [],
      "dependencies": [
        "Vector database",
        "LLM provider"
      ],
      "deployments": [
        "docker",
        "library_only",
        "local",
        "cloud"
      ],
      "difficulty": "intermediate",
      "cloudflare_ready": false,
      "use_cases": [
        "evaluate LLM outputs",
        "benchmark prompts and agents",
        "track model quality"
      ],
      "not_good_for": [
        "edge-only Cloudflare Workers deployment without adaptation",
        "users expecting a complete hosted product"
      ],
      "classification": {
        "category": {
          "confidence": "high",
          "evidence": [
            "Matched \"eval\" in metadata.",
            "Matched \"evaluation\" in metadata."
          ]
        },
        "deployment": {
          "confidence": "high",
          "evidence": [
            "Found Docker configuration file.",
            "Matched \"pip install\" in repository content.",
            "Matched \"npm install\" in repository content.",
            "Matched \"library\" in repository content.",
            "Local usage is assumed for open source repositories unless contradicted."
          ]
        },
        "difficulty": {
          "confidence": "medium",
          "evidence": [
            "No strong beginner or advanced signal found; defaulting to intermediate."
          ]
        },
        "cloudflare_ready": {
          "confidence": "high",
          "evidence": [
            "No Cloudflare deployment signal detected.",
            "No wrangler.toml found in inspected repository files."
          ]
        }
      },
      "quality_signals": {
        "stars": 25434,
        "recent_commits": 100,
        "contributors": 100,
        "issue_response_time_hours": null,
        "release_frequency_180d": 27
      },
      "quality_signal_confidence": {
        "stars_30d_delta": "snapshot",
        "stars30d_window_days": 36,
        "commits_30d": "partial",
        "releases_180d": "complete",
        "contributors_90d": "partial"
      },
      "quality_score": 72,
      "agent_score": 88,
      "score": 93,
      "agent_score_breakdown": {
        "documentation": 90,
        "maintenance": 76,
        "deployment": 90,
        "popularity": 88,
        "community": 100
      },
      "git_top_score": 93,
      "git_top_score_breakdown": {
        "community": 100,
        "maintenance": 84,
        "documentation": 84,
        "stability": 90,
        "adoption": 100,
        "agent_readability": 100
      },
      "verification": {
        "schema_version": "git-top.verification.v1",
        "overall_status": "partial",
        "observed_at": "2026-09-25T08:01:07.646Z",
        "signals": {
          "activity": {
            "status": "observed",
            "source": "github_metadata",
            "evidence": [
              "project.pushed_at",
              "metrics.recent_push_days"
            ]
          },
          "license": {
            "status": "observed",
            "source": "github_metadata",
            "evidence": [
              "project.license"
            ]
          },
          "documentation": {
            "status": "observed",
            "source": "github_metadata",
            "evidence": [
              "project.description"
            ]
          },
          "runtime": {
            "status": "inferred",
            "source": "git_top_heuristic",
            "evidence": [
              "agent_card.deployment",
              "agent_card.cloudflare_ready"
            ]
          },
          "install": {
            "status": "not_run",
            "source": "git_top_runtime",
            "evidence": [
              "installation/build probe is not enabled"
            ]
          },
          "security": {
            "status": "not_run",
            "source": "git_top_runtime",
            "evidence": [
              "dependency/security scan is not enabled"
            ]
          },
          "mcp": {
            "status": "not_applicable",
            "source": "git_top_runtime",
            "evidence": [
              "project is not classified as mcp_server"
            ]
          }
        },
        "coverage": {
          "observed": 3,
          "inferred": 1,
          "not_run": 2,
          "unknown": 0
        },
        "next_steps": [
          "Run an installation/build probe before production adoption.",
          "Run a dependency and security scan before treating the score as a trust claim."
        ]
      },
      "summary": {
        "tl_dr": "Use promptfoo/promptfoo when the user needs a llm eval project with docker, library-only, local deployment options.",
        "purpose": "Use promptfoo/promptfoo when the user needs a llm eval project with docker, library-only, local deployment options.",
        "install": "Run with Docker using the repository's container instructions.",
        "inputs": [
          "prompts",
          "model outputs",
          "test cases"
        ],
        "outputs": [
          "scores",
          "benchmarks",
          "eval reports"
        ],
        "good_for": [
          "evaluate LLM outputs",
          "benchmark prompts and agents",
          "track model quality",
          "model evaluation",
          "benchmarking",
          "regression testing"
        ],
        "not_good_for": [
          "edge-only Cloudflare Workers deployment without adaptation",
          "users expecting a complete hosted product",
          "production inference serving",
          "end-user chat apps"
        ],
        "deployment": [
          "docker",
          "library_only",
          "local",
          "cloud"
        ],
        "alternatives": [
          {
            "repo": "comet-ml/opik",
            "reason": "Same llm eval intent with rag overlap."
          },
          {
            "repo": "Giskard-AI/giskard-oss",
            "reason": "Same llm eval intent with rag overlap."
          },
          {
            "repo": "promptfoo/promptfoo-action",
            "reason": "Same llm eval intent with rag overlap."
          }
        ]
      },
      "evidence": {
        "classification": {
          "category": {
            "confidence": "high",
            "evidence": [
              "Matched \"eval\" in metadata.",
              "Matched \"evaluation\" in metadata."
            ]
          },
          "deployment": {
            "confidence": "high",
            "evidence": [
              "Found Docker configuration file.",
              "Matched \"pip install\" in repository content.",
              "Matched \"npm install\" in repository content.",
              "Matched \"library\" in repository content.",
              "Local usage is assumed for open source repositories unless contradicted."
            ]
          },
          "difficulty": {
            "confidence": "medium",
            "evidence": [
              "No strong beginner or advanced signal found; defaulting to intermediate."
            ]
          },
          "cloudflare_ready": {
            "confidence": "high",
            "evidence": [
              "No Cloudflare deployment signal detected.",
              "No wrangler.toml found in inspected repository files."
            ]
          }
        },
        "quality_signal_confidence": {
          "stars_30d_delta": "snapshot",
          "stars30d_window_days": 36,
          "commits_30d": "partial",
          "releases_180d": "complete",
          "contributors_90d": "partial"
        },
        "verification": {
          "schema_version": "git-top.verification.v1",
          "overall_status": "partial",
          "observed_at": "2026-09-25T08:01:07.646Z",
          "signals": {
            "activity": {
              "status": "observed",
              "source": "github_metadata",
              "evidence": [
                "project.pushed_at",
                "metrics.recent_push_days"
              ]
            },
            "license": {
              "status": "observed",
              "source": "github_metadata",
              "evidence": [
                "project.license"
              ]
            },
            "documentation": {
              "status": "observed",
              "source": "github_metadata",
              "evidence": [
                "project.description"
              ]
            },
            "runtime": {
              "status": "inferred",
              "source": "git_top_heuristic",
              "evidence": [
                "agent_card.deployment",
                "agent_card.cloudflare_ready"
              ]
            },
            "install": {
              "status": "not_run",
              "source": "git_top_runtime",
              "evidence": [
                "installation/build probe is not enabled"
              ]
            },
            "security": {
              "status": "not_run",
              "source": "git_top_runtime",
              "evidence": [
                "dependency/security scan is not enabled"
              ]
            },
            "mcp": {
              "status": "not_applicable",
              "source": "git_top_runtime",
              "evidence": [
                "project is not classified as mcp_server"
              ]
            }
          },
          "coverage": {
            "observed": 3,
            "inferred": 1,
            "not_run": 2,
            "unknown": 0
          },
          "next_steps": [
            "Run an installation/build probe before production adoption.",
            "Run a dependency and security scan before treating the score as a trust claim."
          ]
        },
        "source_fields": [
          "project.description",
          "project.topics",
          "project.language",
          "project.license",
          "agent_card.summary_for_agent",
          "agent_card.use_cases",
          "agent_card.deployment",
          "agent_card.classification",
          "metrics",
          "verification.signals"
        ],
        "caveats": [
          "edge-only Cloudflare Workers deployment without adaptation",
          "users expecting a complete hosted product",
          "Partial or estimated quality signals: commits30d, contributors90d.",
          "Independent installation, security, or runtime probes have not been run for this project."
        ],
        "confidence_reason": "Evidence is usable for comparison, but agents should cite caveats before making a strong recommendation.",
        "last_verified_at": "2026-09-25T08:01:07.646Z"
      },
      "caveats": [
        "edge-only Cloudflare Workers deployment without adaptation",
        "users expecting a complete hosted product",
        "Partial or estimated quality signals: commits30d, contributors90d.",
        "Independent installation, security, or runtime probes have not been run for this project."
      ],
      "confidence_reason": "Evidence is usable for comparison, but agents should cite caveats before making a strong recommendation.",
      "source_fields": [
        "project.description",
        "project.topics",
        "project.language",
        "project.license",
        "agent_card.summary_for_agent",
        "agent_card.use_cases",
        "agent_card.deployment",
        "agent_card.classification",
        "metrics",
        "verification.signals"
      ],
      "last_verified_at": "2026-09-25T08:01:07.646Z"
    },
    {
      "project_id": "langfuse/langfuse",
      "repo": "langfuse/langfuse",
      "name": "langfuse",
      "github_url": "https://github.com/langfuse/langfuse",
      "homepage_url": "https://langfuse.com",
      "language": "TypeScript",
      "license": "NOASSERTION",
      "project_kind": "project",
      "category": [
        "llm_eval"
      ],
      "tags": [
        "analytics",
        "autogen",
        "evaluation",
        "langchain",
        "large-language-models",
        "llama-index",
        "llm",
        "llm-evaluation",
        "llm-observability",
        "llmops",
        "monitoring",
        "observability",
        "open-source",
        "openai",
        "playground",
        "prompt-engineering",
        "prompt-management",
        "self-hosted",
        "ycombinator"
      ],
      "description": "🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.",
      "overview": "Use langfuse/langfuse when the user needs a llm eval project with docker, vercel, serverless deployment options.",
      "alternatives": [
        {
          "repo": "langwatch/langwatch",
          "reason": "Same llm eval intent with observability overlap."
        },
        {
          "repo": "lmnr-ai/lmnr",
          "reason": "Same llm eval intent with observability overlap."
        },
        {
          "repo": "Helicone/helicone",
          "reason": "Same llm eval intent with observability overlap."
        }
      ],
      "related": [],
      "dependencies": [
        "LLM provider"
      ],
      "deployments": [
        "docker",
        "vercel",
        "serverless",
        "kubernetes",
        "library_only",
        "local"
      ],
      "difficulty": "advanced",
      "cloudflare_ready": false,
      "use_cases": [
        "evaluate LLM outputs",
        "benchmark prompts and agents",
        "track model quality"
      ],
      "not_good_for": [
        "edge-only Cloudflare Workers deployment without adaptation",
        "users expecting a complete hosted product"
      ],
      "classification": {
        "category": {
          "confidence": "high",
          "evidence": [
            "Matched \"eval\" in metadata.",
            "Matched \"evaluation\" in metadata."
          ]
        },
        "deployment": {
          "confidence": "high",
          "evidence": [
            "Found Docker configuration file.",
            "Matched \"vercel\" in repository content.",
            "Matched \"kubernetes\" in repository content.",
            "Matched \"pip install\" in repository content.",
            "Matched \"library\" in repository content.",
            "Local usage is assumed for open source repositories unless contradicted."
          ]
        },
        "difficulty": {
          "confidence": "medium",
          "evidence": [
            "Found multi-service or orchestration configuration files."
          ]
        },
        "cloudflare_ready": {
          "confidence": "high",
          "evidence": [
            "Runtime blocker: python, docker daemon.",
            "No Cloudflare deployment signal detected.",
            "No wrangler.toml found in inspected repository files."
          ]
        }
      },
      "quality_signals": {
        "stars": 35033,
        "recent_commits": 100,
        "contributors": 100,
        "issue_response_time_hours": null,
        "release_frequency_180d": 100
      },
      "quality_signal_confidence": {
        "stars_30d_delta": "snapshot",
        "stars30d_window_days": 30,
        "commits_30d": "partial",
        "releases_180d": "partial",
        "contributors_90d": "partial"
      },
      "quality_score": 80,
      "agent_score": 90,
      "score": 93,
      "agent_score_breakdown": {
        "documentation": 90,
        "maintenance": 76,
        "deployment": 100,
        "popularity": 91,
        "community": 100
      },
      "git_top_score": 93,
      "git_top_score_breakdown": {
        "community": 100,
        "maintenance": 84,
        "documentation": 84,
        "stability": 90,
        "adoption": 100,
        "agent_readability": 100
      },
      "verification": {
        "schema_version": "git-top.verification.v1",
        "overall_status": "partial",
        "observed_at": "2026-09-25T11:01:14.293Z",
        "signals": {
          "activity": {
            "status": "observed",
            "source": "github_metadata",
            "evidence": [
              "project.pushed_at",
              "metrics.recent_push_days"
            ]
          },
          "license": {
            "status": "observed",
            "source": "github_metadata",
            "evidence": [
              "project.license"
            ]
          },
          "documentation": {
            "status": "observed",
            "source": "github_metadata",
            "evidence": [
              "project.description"
            ]
          },
          "runtime": {
            "status": "inferred",
            "source": "git_top_heuristic",
            "evidence": [
              "agent_card.deployment",
              "agent_card.cloudflare_ready"
            ]
          },
          "install": {
            "status": "not_run",
            "source": "git_top_runtime",
            "evidence": [
              "installation/build probe is not enabled"
            ]
          },
          "security": {
            "status": "not_run",
            "source": "git_top_runtime",
            "evidence": [
              "dependency/security scan is not enabled"
            ]
          },
          "mcp": {
            "status": "not_applicable",
            "source": "git_top_runtime",
            "evidence": [
              "project is not classified as mcp_server"
            ]
          }
        },
        "coverage": {
          "observed": 3,
          "inferred": 1,
          "not_run": 2,
          "unknown": 0
        },
        "next_steps": [
          "Run an installation/build probe before production adoption.",
          "Run a dependency and security scan before treating the score as a trust claim."
        ]
      },
      "summary": {
        "tl_dr": "Use langfuse/langfuse when the user needs a llm eval project with docker, vercel, serverless deployment options.",
        "purpose": "Use langfuse/langfuse when the user needs a llm eval project with docker, vercel, serverless deployment options.",
        "install": "Run with Docker using the repository's container instructions.",
        "inputs": [
          "prompts",
          "model outputs",
          "test cases"
        ],
        "outputs": [
          "scores",
          "benchmarks",
          "eval reports"
        ],
        "good_for": [
          "evaluate LLM outputs",
          "benchmark prompts and agents",
          "track model quality",
          "model evaluation",
          "benchmarking",
          "regression testing"
        ],
        "not_good_for": [
          "edge-only Cloudflare Workers deployment without adaptation",
          "users expecting a complete hosted product",
          "production inference serving",
          "end-user chat apps"
        ],
        "deployment": [
          "docker",
          "vercel",
          "serverless",
          "kubernetes",
          "library_only",
          "local"
        ],
        "alternatives": [
          {
            "repo": "langwatch/langwatch",
            "reason": "Same llm eval intent with observability overlap."
          },
          {
            "repo": "lmnr-ai/lmnr",
            "reason": "Same llm eval intent with observability overlap."
          },
          {
            "repo": "Helicone/helicone",
            "reason": "Same llm eval intent with observability overlap."
          }
        ]
      },
      "evidence": {
        "classification": {
          "category": {
            "confidence": "high",
            "evidence": [
              "Matched \"eval\" in metadata.",
              "Matched \"evaluation\" in metadata."
            ]
          },
          "deployment": {
            "confidence": "high",
            "evidence": [
              "Found Docker configuration file.",
              "Matched \"vercel\" in repository content.",
              "Matched \"kubernetes\" in repository content.",
              "Matched \"pip install\" in repository content.",
              "Matched \"library\" in repository content.",
              "Local usage is assumed for open source repositories unless contradicted."
            ]
          },
          "difficulty": {
            "confidence": "medium",
            "evidence": [
              "Found multi-service or orchestration configuration files."
            ]
          },
          "cloudflare_ready": {
            "confidence": "high",
            "evidence": [
              "Runtime blocker: python, docker daemon.",
              "No Cloudflare deployment signal detected.",
              "No wrangler.toml found in inspected repository files."
            ]
          }
        },
        "quality_signal_confidence": {
          "stars_30d_delta": "snapshot",
          "stars30d_window_days": 30,
          "commits_30d": "partial",
          "releases_180d": "partial",
          "contributors_90d": "partial"
        },
        "verification": {
          "schema_version": "git-top.verification.v1",
          "overall_status": "partial",
          "observed_at": "2026-09-25T11:01:14.293Z",
          "signals": {
            "activity": {
              "status": "observed",
              "source": "github_metadata",
              "evidence": [
                "project.pushed_at",
                "metrics.recent_push_days"
              ]
            },
            "license": {
              "status": "observed",
              "source": "github_metadata",
              "evidence": [
                "project.license"
              ]
            },
            "documentation": {
              "status": "observed",
              "source": "github_metadata",
              "evidence": [
                "project.description"
              ]
            },
            "runtime": {
              "status": "inferred",
              "source": "git_top_heuristic",
              "evidence": [
                "agent_card.deployment",
                "agent_card.cloudflare_ready"
              ]
            },
            "install": {
              "status": "not_run",
              "source": "git_top_runtime",
              "evidence": [
                "installation/build probe is not enabled"
              ]
            },
            "security": {
              "status": "not_run",
              "source": "git_top_runtime",
              "evidence": [
                "dependency/security scan is not enabled"
              ]
            },
            "mcp": {
              "status": "not_applicable",
              "source": "git_top_runtime",
              "evidence": [
                "project is not classified as mcp_server"
              ]
            }
          },
          "coverage": {
            "observed": 3,
            "inferred": 1,
            "not_run": 2,
            "unknown": 0
          },
          "next_steps": [
            "Run an installation/build probe before production adoption.",
            "Run a dependency and security scan before treating the score as a trust claim."
          ]
        },
        "source_fields": [
          "project.description",
          "project.topics",
          "project.language",
          "project.license",
          "agent_card.summary_for_agent",
          "agent_card.use_cases",
          "agent_card.deployment",
          "agent_card.classification",
          "metrics",
          "verification.signals"
        ],
        "caveats": [
          "edge-only Cloudflare Workers deployment without adaptation",
          "users expecting a complete hosted product",
          "Partial or estimated quality signals: commits30d, releases180d, contributors90d.",
          "Independent installation, security, or runtime probes have not been run for this project."
        ],
        "confidence_reason": "Evidence is usable for comparison, but agents should cite caveats before making a strong recommendation.",
        "last_verified_at": "2026-09-25T11:01:14.293Z"
      },
      "caveats": [
        "edge-only Cloudflare Workers deployment without adaptation",
        "users expecting a complete hosted product",
        "Partial or estimated quality signals: commits30d, releases180d, contributors90d.",
        "Independent installation, security, or runtime probes have not been run for this project."
      ],
      "confidence_reason": "Evidence is usable for comparison, but agents should cite caveats before making a strong recommendation.",
      "source_fields": [
        "project.description",
        "project.topics",
        "project.language",
        "project.license",
        "agent_card.summary_for_agent",
        "agent_card.use_cases",
        "agent_card.deployment",
        "agent_card.classification",
        "metrics",
        "verification.signals"
      ],
      "last_verified_at": "2026-09-25T11:01:14.293Z"
    },
    {
      "project_id": "ai-twinkle/Eval",
      "repo": "ai-twinkle/Eval",
      "name": "Eval",
      "github_url": "https://github.com/ai-twinkle/Eval",
      "homepage_url": "https://twinkleai.tw",
      "language": "Python",
      "license": "MIT",
      "project_kind": "project",
      "category": [
        "llm_eval"
      ],
      "tags": [
        "eval",
        "evaluation",
        "llm"
      ],
      "description": "High-performance LLM evaluation framework with parallel API calls — up to 17× faster than sequential tools. Supports box, math, and logit-based evaluation.",
      "overview": "Use ai-twinkle/Eval when the user needs a llm eval project with docker, library-only, local deployment options.",
      "alternatives": [
        {
          "repo": "comet-ml/opik",
          "reason": "Similar llm eval with docker/library_only deployment overlap."
        },
        {
          "repo": "modelscope/evalscope",
          "reason": "Similar llm eval with docker/library_only deployment overlap."
        },
        {
          "repo": "agentevals-dev/agentevals",
          "reason": "Similar llm eval with docker/library_only deployment overlap."
        }
      ],
      "related": [],
      "dependencies": [
        "LLM provider"
      ],
      "deployments": [
        "docker",
        "library_only",
        "local",
        "cloud"
      ],
      "difficulty": "beginner",
      "cloudflare_ready": false,
      "use_cases": [
        "evaluate LLM outputs",
        "benchmark prompts and agents",
        "track model quality"
      ],
      "not_good_for": [
        "edge-only Cloudflare Workers deployment without adaptation",
        "users expecting a complete hosted product"
      ],
      "classification": {
        "category": {
          "confidence": "high",
          "evidence": [
            "Matched \"eval\" in metadata.",
            "Matched \"evaluation\" in metadata."
          ]
        },
        "deployment": {
          "confidence": "high",
          "evidence": [
            "Found Docker configuration file.",
            "Matched \"pip install\" in repository content.",
            "Local usage is assumed for open source repositories unless contradicted."
          ]
        },
        "difficulty": {
          "confidence": "medium",
          "evidence": [
            "Repository has under 10k stars, so complexity is treated conservatively."
          ]
        },
        "cloudflare_ready": {
          "confidence": "high",
          "evidence": [
            "Runtime blocker: python, gpu.",
            "No Cloudflare deployment signal detected.",
            "No wrangler.toml found in inspected repository files."
          ]
        }
      },
      "quality_signals": {
        "stars": 117,
        "recent_commits": 27,
        "contributors": 7,
        "issue_response_time_hours": null,
        "release_frequency_180d": 8
      },
      "quality_signal_confidence": {
        "stars_30d_delta": "snapshot",
        "stars30d_window_days": 36,
        "commits_30d": "complete",
        "releases_180d": "complete",
        "contributors_90d": "complete"
      },
      "quality_score": 19,
      "agent_score": 62,
      "score": 79,
      "agent_score_breakdown": {
        "documentation": 90,
        "maintenance": 36,
        "deployment": 90,
        "popularity": 41,
        "community": 52
      },
      "git_top_score": 79,
      "git_top_score_breakdown": {
        "community": 84,
        "maintenance": 56,
        "documentation": 84,
        "stability": 100,
        "adoption": 58,
        "agent_readability": 100
      },
      "verification": {
        "schema_version": "git-top.verification.v1",
        "overall_status": "partial",
        "observed_at": "2026-09-22T19:31:05.843Z",
        "signals": {
          "activity": {
            "status": "observed",
            "source": "github_metadata",
            "evidence": [
              "project.pushed_at",
              "metrics.recent_push_days"
            ]
          },
          "license": {
            "status": "observed",
            "source": "github_metadata",
            "evidence": [
              "project.license"
            ]
          },
          "documentation": {
            "status": "observed",
            "source": "github_metadata",
            "evidence": [
              "project.description"
            ]
          },
          "runtime": {
            "status": "inferred",
            "source": "git_top_heuristic",
            "evidence": [
              "agent_card.deployment",
              "agent_card.cloudflare_ready"
            ]
          },
          "install": {
            "status": "not_run",
            "source": "git_top_runtime",
            "evidence": [
              "installation/build probe is not enabled"
            ]
          },
          "security": {
            "status": "not_run",
            "source": "git_top_runtime",
            "evidence": [
              "dependency/security scan is not enabled"
            ]
          },
          "mcp": {
            "status": "not_applicable",
            "source": "git_top_runtime",
            "evidence": [
              "project is not classified as mcp_server"
            ]
          }
        },
        "coverage": {
          "observed": 3,
          "inferred": 1,
          "not_run": 2,
          "unknown": 0
        },
        "next_steps": [
          "Run an installation/build probe before production adoption.",
          "Run a dependency and security scan before treating the score as a trust claim."
        ]
      },
      "summary": {
        "tl_dr": "Use ai-twinkle/Eval when the user needs a llm eval project with docker, library-only, local deployment options.",
        "purpose": "Use ai-twinkle/Eval when the user needs a llm eval project with docker, library-only, local deployment options.",
        "install": "Run with Docker using the repository's container instructions.",
        "inputs": [
          "prompts",
          "model outputs",
          "test cases"
        ],
        "outputs": [
          "scores",
          "benchmarks",
          "eval reports"
        ],
        "good_for": [
          "evaluate LLM outputs",
          "benchmark prompts and agents",
          "track model quality",
          "model evaluation",
          "benchmarking",
          "regression testing"
        ],
        "not_good_for": [
          "edge-only Cloudflare Workers deployment without adaptation",
          "users expecting a complete hosted product",
          "production inference serving",
          "end-user chat apps"
        ],
        "deployment": [
          "docker",
          "library_only",
          "local",
          "cloud"
        ],
        "alternatives": [
          {
            "repo": "comet-ml/opik",
            "reason": "Similar llm eval with docker/library_only deployment overlap."
          },
          {
            "repo": "modelscope/evalscope",
            "reason": "Similar llm eval with docker/library_only deployment overlap."
          },
          {
            "repo": "agentevals-dev/agentevals",
            "reason": "Similar llm eval with docker/library_only deployment overlap."
          }
        ]
      },
      "evidence": {
        "classification": {
          "category": {
            "confidence": "high",
            "evidence": [
              "Matched \"eval\" in metadata.",
              "Matched \"evaluation\" in metadata."
            ]
          },
          "deployment": {
            "confidence": "high",
            "evidence": [
              "Found Docker configuration file.",
              "Matched \"pip install\" in repository content.",
              "Local usage is assumed for open source repositories unless contradicted."
            ]
          },
          "difficulty": {
            "confidence": "medium",
            "evidence": [
              "Repository has under 10k stars, so complexity is treated conservatively."
            ]
          },
          "cloudflare_ready": {
            "confidence": "high",
            "evidence": [
              "Runtime blocker: python, gpu.",
              "No Cloudflare deployment signal detected.",
              "No wrangler.toml found in inspected repository files."
            ]
          }
        },
        "quality_signal_confidence": {
          "stars_30d_delta": "snapshot",
          "stars30d_window_days": 36,
          "commits_30d": "complete",
          "releases_180d": "complete",
          "contributors_90d": "complete"
        },
        "verification": {
          "schema_version": "git-top.verification.v1",
          "overall_status": "partial",
          "observed_at": "2026-09-22T19:31:05.843Z",
          "signals": {
            "activity": {
              "status": "observed",
              "source": "github_metadata",
              "evidence": [
                "project.pushed_at",
                "metrics.recent_push_days"
              ]
            },
            "license": {
              "status": "observed",
              "source": "github_metadata",
              "evidence": [
                "project.license"
              ]
            },
            "documentation": {
              "status": "observed",
              "source": "github_metadata",
              "evidence": [
                "project.description"
              ]
            },
            "runtime": {
              "status": "inferred",
              "source": "git_top_heuristic",
              "evidence": [
                "agent_card.deployment",
                "agent_card.cloudflare_ready"
              ]
            },
            "install": {
              "status": "not_run",
              "source": "git_top_runtime",
              "evidence": [
                "installation/build probe is not enabled"
              ]
            },
            "security": {
              "status": "not_run",
              "source": "git_top_runtime",
              "evidence": [
                "dependency/security scan is not enabled"
              ]
            },
            "mcp": {
              "status": "not_applicable",
              "source": "git_top_runtime",
              "evidence": [
                "project is not classified as mcp_server"
              ]
            }
          },
          "coverage": {
            "observed": 3,
            "inferred": 1,
            "not_run": 2,
            "unknown": 0
          },
          "next_steps": [
            "Run an installation/build probe before production adoption.",
            "Run a dependency and security scan before treating the score as a trust claim."
          ]
        },
        "source_fields": [
          "project.description",
          "project.topics",
          "project.language",
          "project.license",
          "agent_card.summary_for_agent",
          "agent_card.use_cases",
          "agent_card.deployment",
          "agent_card.classification",
          "metrics",
          "verification.signals"
        ],
        "caveats": [
          "edge-only Cloudflare Workers deployment without adaptation",
          "users expecting a complete hosted product",
          "Independent installation, security, or runtime probes have not been run for this project."
        ],
        "confidence_reason": "Classification evidence and quality signals are strong enough for shortlist reasoning when metadata is current.",
        "last_verified_at": "2026-09-22T19:31:05.843Z"
      },
      "caveats": [
        "edge-only Cloudflare Workers deployment without adaptation",
        "users expecting a complete hosted product",
        "Independent installation, security, or runtime probes have not been run for this project."
      ],
      "confidence_reason": "Classification evidence and quality signals are strong enough for shortlist reasoning when metadata is current.",
      "source_fields": [
        "project.description",
        "project.topics",
        "project.language",
        "project.license",
        "agent_card.summary_for_agent",
        "agent_card.use_cases",
        "agent_card.deployment",
        "agent_card.classification",
        "metrics",
        "verification.signals"
      ],
      "last_verified_at": "2026-09-22T19:31:05.843Z"
    },
    {
      "project_id": "EricLBuehler/mistral.rs",
      "repo": "EricLBuehler/mistral.rs",
      "name": "mistral.rs",
      "github_url": "https://github.com/EricLBuehler/mistral.rs",
      "homepage_url": null,
      "language": "Rust",
      "license": "MIT",
      "project_kind": "project",
      "category": [
        "llm_eval"
      ],
      "tags": [
        "llm",
        "rust",
        "uqff"
      ],
      "description": "Fast, flexible LLM inference",
      "overview": "Use EricLBuehler/mistral.rs when the user needs a llm eval project with docker, kubernetes, library-only deployment options.",
      "alternatives": [
        {
          "repo": "promptfoo/promptfoo",
          "reason": "Similar llm eval with docker/library_only deployment overlap."
        },
        {
          "repo": "comet-ml/opik",
          "reason": "Similar llm eval with docker/kubernetes deployment overlap."
        },
        {
          "repo": "huggingface/text-embeddings-inference",
          "reason": "Similar llm eval with docker/local deployment overlap."
        }
      ],
      "related": [],
      "dependencies": [
        "LLM provider"
      ],
      "deployments": [
        "docker",
        "kubernetes",
        "library_only",
        "local",
        "cloud"
      ],
      "difficulty": "beginner",
      "cloudflare_ready": false,
      "use_cases": [
        "evaluate LLM outputs",
        "benchmark prompts and agents",
        "track model quality"
      ],
      "not_good_for": [
        "edge-only Cloudflare Workers deployment without adaptation",
        "users expecting a complete hosted product"
      ],
      "classification": {
        "category": {
          "confidence": "medium",
          "evidence": [
            "Matched \"benchmark\" in repository content."
          ]
        },
        "deployment": {
          "confidence": "high",
          "evidence": [
            "Found Docker configuration file.",
            "Matched \"kubernetes\" in repository content.",
            "Matched \"pip install\" in repository content.",
            "Local usage is assumed for open source repositories unless contradicted."
          ]
        },
        "difficulty": {
          "confidence": "medium",
          "evidence": [
            "Repository has under 10k stars, so complexity is treated conservatively."
          ]
        },
        "cloudflare_ready": {
          "confidence": "high",
          "evidence": [
            "Runtime blocker: python, cuda, gpu.",
            "No Cloudflare deployment signal detected.",
            "No wrangler.toml found in inspected repository files."
          ]
        }
      },
      "quality_signals": {
        "stars": 7718,
        "recent_commits": 36,
        "contributors": 95,
        "issue_response_time_hours": null,
        "release_frequency_180d": 35
      },
      "quality_signal_confidence": {
        "stars_30d_delta": "snapshot",
        "stars30d_window_days": 30,
        "commits_30d": "complete",
        "releases_180d": "complete",
        "contributors_90d": "complete"
      },
      "quality_score": 40,
      "agent_score": 86,
      "score": 93,
      "agent_score_breakdown": {
        "documentation": 90,
        "maintenance": 66,
        "deployment": 100,
        "popularity": 78,
        "community": 100
      },
      "git_top_score": 93,
      "git_top_score_breakdown": {
        "community": 100,
        "maintenance": 77,
        "documentation": 92,
        "stability": 90,
        "adoption": 100,
        "agent_readability": 100
      },
      "verification": {
        "schema_version": "git-top.verification.v1",
        "overall_status": "partial",
        "observed_at": "2026-09-25T04:31:17.138Z",
        "signals": {
          "activity": {
            "status": "observed",
            "source": "github_metadata",
            "evidence": [
              "project.pushed_at",
              "metrics.recent_push_days"
            ]
          },
          "license": {
            "status": "observed",
            "source": "github_metadata",
            "evidence": [
              "project.license"
            ]
          },
          "documentation": {
            "status": "observed",
            "source": "github_metadata",
            "evidence": [
              "project.description"
            ]
          },
          "runtime": {
            "status": "inferred",
            "source": "git_top_heuristic",
            "evidence": [
              "agent_card.deployment",
              "agent_card.cloudflare_ready"
            ]
          },
          "install": {
            "status": "not_run",
            "source": "git_top_runtime",
            "evidence": [
              "installation/build probe is not enabled"
            ]
          },
          "security": {
            "status": "not_run",
            "source": "git_top_runtime",
            "evidence": [
              "dependency/security scan is not enabled"
            ]
          },
          "mcp": {
            "status": "not_applicable",
            "source": "git_top_runtime",
            "evidence": [
              "project is not classified as mcp_server"
            ]
          }
        },
        "coverage": {
          "observed": 3,
          "inferred": 1,
          "not_run": 2,
          "unknown": 0
        },
        "next_steps": [
          "Run an installation/build probe before production adoption.",
          "Run a dependency and security scan before treating the score as a trust claim."
        ]
      },
      "summary": {
        "tl_dr": "Use EricLBuehler/mistral.rs when the user needs a llm eval project with docker, kubernetes, library-only deployment options.",
        "purpose": "Use EricLBuehler/mistral.rs when the user needs a llm eval project with docker, kubernetes, library-only deployment options.",
        "install": "Run with Docker using the repository's container instructions.",
        "inputs": [
          "prompts",
          "model outputs",
          "test cases"
        ],
        "outputs": [
          "scores",
          "benchmarks",
          "eval reports"
        ],
        "good_for": [
          "evaluate LLM outputs",
          "benchmark prompts and agents",
          "track model quality",
          "model evaluation",
          "benchmarking",
          "regression testing"
        ],
        "not_good_for": [
          "edge-only Cloudflare Workers deployment without adaptation",
          "users expecting a complete hosted product",
          "production inference serving",
          "end-user chat apps"
        ],
        "deployment": [
          "docker",
          "kubernetes",
          "library_only",
          "local",
          "cloud"
        ],
        "alternatives": [
          {
            "repo": "promptfoo/promptfoo",
            "reason": "Similar llm eval with docker/library_only deployment overlap."
          },
          {
            "repo": "comet-ml/opik",
            "reason": "Similar llm eval with docker/kubernetes deployment overlap."
          },
          {
            "repo": "huggingface/text-embeddings-inference",
            "reason": "Similar llm eval with docker/local deployment overlap."
          }
        ]
      },
      "evidence": {
        "classification": {
          "category": {
            "confidence": "medium",
            "evidence": [
              "Matched \"benchmark\" in repository content."
            ]
          },
          "deployment": {
            "confidence": "high",
            "evidence": [
              "Found Docker configuration file.",
              "Matched \"kubernetes\" in repository content.",
              "Matched \"pip install\" in repository content.",
              "Local usage is assumed for open source repositories unless contradicted."
            ]
          },
          "difficulty": {
            "confidence": "medium",
            "evidence": [
              "Repository has under 10k stars, so complexity is treated conservatively."
            ]
          },
          "cloudflare_ready": {
            "confidence": "high",
            "evidence": [
              "Runtime blocker: python, cuda, gpu.",
              "No Cloudflare deployment signal detected.",
              "No wrangler.toml found in inspected repository files."
            ]
          }
        },
        "quality_signal_confidence": {
          "stars_30d_delta": "snapshot",
          "stars30d_window_days": 30,
          "commits_30d": "complete",
          "releases_180d": "complete",
          "contributors_90d": "complete"
        },
        "verification": {
          "schema_version": "git-top.verification.v1",
          "overall_status": "partial",
          "observed_at": "2026-09-25T04:31:17.138Z",
          "signals": {
            "activity": {
              "status": "observed",
              "source": "github_metadata",
              "evidence": [
                "project.pushed_at",
                "metrics.recent_push_days"
              ]
            },
            "license": {
              "status": "observed",
              "source": "github_metadata",
              "evidence": [
                "project.license"
              ]
            },
            "documentation": {
              "status": "observed",
              "source": "github_metadata",
              "evidence": [
                "project.description"
              ]
            },
            "runtime": {
              "status": "inferred",
              "source": "git_top_heuristic",
              "evidence": [
                "agent_card.deployment",
                "agent_card.cloudflare_ready"
              ]
            },
            "install": {
              "status": "not_run",
              "source": "git_top_runtime",
              "evidence": [
                "installation/build probe is not enabled"
              ]
            },
            "security": {
              "status": "not_run",
              "source": "git_top_runtime",
              "evidence": [
                "dependency/security scan is not enabled"
              ]
            },
            "mcp": {
              "status": "not_applicable",
              "source": "git_top_runtime",
              "evidence": [
                "project is not classified as mcp_server"
              ]
            }
          },
          "coverage": {
            "observed": 3,
            "inferred": 1,
            "not_run": 2,
            "unknown": 0
          },
          "next_steps": [
            "Run an installation/build probe before production adoption.",
            "Run a dependency and security scan before treating the score as a trust claim."
          ]
        },
        "source_fields": [
          "project.description",
          "project.topics",
          "project.language",
          "project.license",
          "agent_card.summary_for_agent",
          "agent_card.use_cases",
          "agent_card.deployment",
          "agent_card.classification",
          "metrics",
          "verification.signals"
        ],
        "caveats": [
          "edge-only Cloudflare Workers deployment without adaptation",
          "users expecting a complete hosted product",
          "Independent installation, security, or runtime probes have not been run for this project."
        ],
        "confidence_reason": "Evidence is usable for comparison, but agents should cite caveats before making a strong recommendation.",
        "last_verified_at": "2026-09-25T04:31:17.138Z"
      },
      "caveats": [
        "edge-only Cloudflare Workers deployment without adaptation",
        "users expecting a complete hosted product",
        "Independent installation, security, or runtime probes have not been run for this project."
      ],
      "confidence_reason": "Evidence is usable for comparison, but agents should cite caveats before making a strong recommendation.",
      "source_fields": [
        "project.description",
        "project.topics",
        "project.language",
        "project.license",
        "agent_card.summary_for_agent",
        "agent_card.use_cases",
        "agent_card.deployment",
        "agent_card.classification",
        "metrics",
        "verification.signals"
      ],
      "last_verified_at": "2026-09-25T04:31:17.138Z"
    },
    {
      "project_id": "coze-dev/coze-loop",
      "repo": "coze-dev/coze-loop",
      "name": "coze-loop",
      "github_url": "https://github.com/coze-dev/coze-loop",
      "homepage_url": null,
      "language": "Go",
      "license": "Apache-2.0",
      "project_kind": "project",
      "category": [
        "llm_eval"
      ],
      "tags": [
        "agent",
        "agent-evaluation",
        "agent-observability",
        "agentops",
        "ai",
        "coze",
        "eino",
        "evaluation",
        "langchain",
        "llm-observability",
        "llmops",
        "monitoring",
        "observability",
        "open-source",
        "openai",
        "playground",
        "prompt-management"
      ],
      "description": "Next-generation AI Agent Optimization Platform: Cozeloop addresses challenges in AI agent development by providing full-lifecycle management capabilities from development, debugging, and evaluation to monitoring.  ",
      "overview": "Use coze-dev/coze-loop when the user needs a llm eval project with docker, kubernetes, local deployment options.",
      "alternatives": [
        {
          "repo": "langwatch/langwatch",
          "reason": "Same llm eval intent with observability overlap."
        },
        {
          "repo": "comet-ml/opik",
          "reason": "Same llm eval intent with observability overlap."
        },
        {
          "repo": "Arize-ai/phoenix",
          "reason": "Same llm eval intent with observability overlap."
        }
      ],
      "related": [],
      "dependencies": [
        "LLM provider"
      ],
      "deployments": [
        "docker",
        "kubernetes",
        "local",
        "cloud"
      ],
      "difficulty": "beginner",
      "cloudflare_ready": false,
      "use_cases": [
        "evaluate LLM outputs",
        "benchmark prompts and agents",
        "track model quality"
      ],
      "not_good_for": [
        "edge-only Cloudflare Workers deployment without adaptation"
      ],
      "classification": {
        "category": {
          "confidence": "high",
          "evidence": [
            "Matched \"eval\" in metadata.",
            "Matched \"evaluation\" in metadata."
          ]
        },
        "deployment": {
          "confidence": "high",
          "evidence": [
            "Matched \"kubernetes\" in repository content.",
            "Matched \"helm chart\" in repository content.",
            "Local usage is assumed for open source repositories unless contradicted."
          ]
        },
        "difficulty": {
          "confidence": "medium",
          "evidence": [
            "Repository has under 10k stars, so complexity is treated conservatively."
          ]
        },
        "cloudflare_ready": {
          "confidence": "high",
          "evidence": [
            "No Cloudflare deployment signal detected.",
            "No wrangler.toml found in inspected repository files."
          ]
        }
      },
      "quality_signals": {
        "stars": 5740,
        "recent_commits": 29,
        "contributors": 44,
        "issue_response_time_hours": null,
        "release_frequency_180d": 0
      },
      "quality_signal_confidence": {
        "stars_30d_delta": "snapshot",
        "stars30d_window_days": 34,
        "commits_30d": "complete",
        "releases_180d": "complete",
        "contributors_90d": "complete"
      },
      "quality_score": 16,
      "agent_score": 73,
      "score": 81,
      "agent_score_breakdown": {
        "documentation": 90,
        "maintenance": 30,
        "deployment": 90,
        "popularity": 75,
        "community": 89
      },
      "git_top_score": 81,
      "git_top_score_breakdown": {
        "community": 100,
        "maintenance": 40,
        "documentation": 84,
        "stability": 70,
        "adoption": 100,
        "agent_readability": 100
      },
      "verification": {
        "schema_version": "git-top.verification.v1",
        "overall_status": "partial",
        "observed_at": "2026-09-20T14:31:08.641Z",
        "signals": {
          "activity": {
            "status": "observed",
            "source": "github_metadata",
            "evidence": [
              "project.pushed_at",
              "metrics.recent_push_days"
            ]
          },
          "license": {
            "status": "observed",
            "source": "github_metadata",
            "evidence": [
              "project.license"
            ]
          },
          "documentation": {
            "status": "observed",
            "source": "github_metadata",
            "evidence": [
              "project.description"
            ]
          },
          "runtime": {
            "status": "inferred",
            "source": "git_top_heuristic",
            "evidence": [
              "agent_card.deployment",
              "agent_card.cloudflare_ready"
            ]
          },
          "install": {
            "status": "not_run",
            "source": "git_top_runtime",
            "evidence": [
              "installation/build probe is not enabled"
            ]
          },
          "security": {
            "status": "not_run",
            "source": "git_top_runtime",
            "evidence": [
              "dependency/security scan is not enabled"
            ]
          },
          "mcp": {
            "status": "not_applicable",
            "source": "git_top_runtime",
            "evidence": [
              "project is not classified as mcp_server"
            ]
          }
        },
        "coverage": {
          "observed": 3,
          "inferred": 1,
          "not_run": 2,
          "unknown": 0
        },
        "next_steps": [
          "Run an installation/build probe before production adoption.",
          "Run a dependency and security scan before treating the score as a trust claim."
        ]
      },
      "summary": {
        "tl_dr": "Use coze-dev/coze-loop when the user needs a llm eval project with docker, kubernetes, local deployment options.",
        "purpose": "Use coze-dev/coze-loop when the user needs a llm eval project with docker, kubernetes, local deployment options.",
        "install": "Run with Docker using the repository's container instructions.",
        "inputs": [
          "prompts",
          "model outputs",
          "test cases"
        ],
        "outputs": [
          "scores",
          "benchmarks",
          "eval reports"
        ],
        "good_for": [
          "evaluate LLM outputs",
          "benchmark prompts and agents",
          "track model quality",
          "model evaluation",
          "benchmarking",
          "regression testing"
        ],
        "not_good_for": [
          "edge-only Cloudflare Workers deployment without adaptation",
          "production inference serving",
          "end-user chat apps"
        ],
        "deployment": [
          "docker",
          "kubernetes",
          "local",
          "cloud"
        ],
        "alternatives": [
          {
            "repo": "langwatch/langwatch",
            "reason": "Same llm eval intent with observability overlap."
          },
          {
            "repo": "comet-ml/opik",
            "reason": "Same llm eval intent with observability overlap."
          },
          {
            "repo": "Arize-ai/phoenix",
            "reason": "Same llm eval intent with observability overlap."
          }
        ]
      },
      "evidence": {
        "classification": {
          "category": {
            "confidence": "high",
            "evidence": [
              "Matched \"eval\" in metadata.",
              "Matched \"evaluation\" in metadata."
            ]
          },
          "deployment": {
            "confidence": "high",
            "evidence": [
              "Matched \"kubernetes\" in repository content.",
              "Matched \"helm chart\" in repository content.",
              "Local usage is assumed for open source repositories unless contradicted."
            ]
          },
          "difficulty": {
            "confidence": "medium",
            "evidence": [
              "Repository has under 10k stars, so complexity is treated conservatively."
            ]
          },
          "cloudflare_ready": {
            "confidence": "high",
            "evidence": [
              "No Cloudflare deployment signal detected.",
              "No wrangler.toml found in inspected repository files."
            ]
          }
        },
        "quality_signal_confidence": {
          "stars_30d_delta": "snapshot",
          "stars30d_window_days": 34,
          "commits_30d": "complete",
          "releases_180d": "complete",
          "contributors_90d": "complete"
        },
        "verification": {
          "schema_version": "git-top.verification.v1",
          "overall_status": "partial",
          "observed_at": "2026-09-20T14:31:08.641Z",
          "signals": {
            "activity": {
              "status": "observed",
              "source": "github_metadata",
              "evidence": [
                "project.pushed_at",
                "metrics.recent_push_days"
              ]
            },
            "license": {
              "status": "observed",
              "source": "github_metadata",
              "evidence": [
                "project.license"
              ]
            },
            "documentation": {
              "status": "observed",
              "source": "github_metadata",
              "evidence": [
                "project.description"
              ]
            },
            "runtime": {
              "status": "inferred",
              "source": "git_top_heuristic",
              "evidence": [
                "agent_card.deployment",
                "agent_card.cloudflare_ready"
              ]
            },
            "install": {
              "status": "not_run",
              "source": "git_top_runtime",
              "evidence": [
                "installation/build probe is not enabled"
              ]
            },
            "security": {
              "status": "not_run",
              "source": "git_top_runtime",
              "evidence": [
                "dependency/security scan is not enabled"
              ]
            },
            "mcp": {
              "status": "not_applicable",
              "source": "git_top_runtime",
              "evidence": [
                "project is not classified as mcp_server"
              ]
            }
          },
          "coverage": {
            "observed": 3,
            "inferred": 1,
            "not_run": 2,
            "unknown": 0
          },
          "next_steps": [
            "Run an installation/build probe before production adoption.",
            "Run a dependency and security scan before treating the score as a trust claim."
          ]
        },
        "source_fields": [
          "project.description",
          "project.topics",
          "project.language",
          "project.license",
          "agent_card.summary_for_agent",
          "agent_card.use_cases",
          "agent_card.deployment",
          "agent_card.classification",
          "metrics",
          "verification.signals"
        ],
        "caveats": [
          "edge-only Cloudflare Workers deployment without adaptation",
          "Independent installation, security, or runtime probes have not been run for this project."
        ],
        "confidence_reason": "Classification evidence and quality signals are strong enough for shortlist reasoning when metadata is current.",
        "last_verified_at": "2026-09-20T14:31:08.641Z"
      },
      "caveats": [
        "edge-only Cloudflare Workers deployment without adaptation",
        "Independent installation, security, or runtime probes have not been run for this project."
      ],
      "confidence_reason": "Classification evidence and quality signals are strong enough for shortlist reasoning when metadata is current.",
      "source_fields": [
        "project.description",
        "project.topics",
        "project.language",
        "project.license",
        "agent_card.summary_for_agent",
        "agent_card.use_cases",
        "agent_card.deployment",
        "agent_card.classification",
        "metrics",
        "verification.signals"
      ],
      "last_verified_at": "2026-09-20T14:31:08.641Z"
    },
    {
      "project_id": "dataelement/bisheng",
      "repo": "dataelement/bisheng",
      "name": "bisheng",
      "github_url": "https://github.com/dataelement/bisheng",
      "homepage_url": "http://www.bisheng.ai",
      "language": "Python",
      "license": "Apache-2.0",
      "project_kind": "project",
      "category": [
        "llm_eval"
      ],
      "tags": [
        "agent",
        "ai",
        "chatbot",
        "enterprise",
        "finetune",
        "genai",
        "gpt",
        "langchian",
        "llama",
        "llm",
        "llmdevops",
        "llmops",
        "ocr",
        "openai",
        "orchestration",
        "python",
        "rag",
        "react",
        "sft",
        "workflow"
      ],
      "description": "BISHENG is an open LLM devops platform for next generation Enterprise AI applications. Powerful and comprehensive features include: GenAI workflow, RAG, Agent, Unified model management, Evaluation, SFT, Dataset Management, Enterprise-level System Management, Observability and more.",
      "overview": "Use dataelement/bisheng when the user needs a llm eval project with docker, local, cloud deployment options.",
      "alternatives": [
        {
          "repo": "promptfoo/promptfoo",
          "reason": "Same llm eval intent with rag overlap."
        },
        {
          "repo": "comet-ml/opik",
          "reason": "Same llm eval intent with rag, observability, workflow overlap."
        },
        {
          "repo": "modelscope/evalscope",
          "reason": "Same llm eval intent with rag overlap."
        }
      ],
      "related": [],
      "dependencies": [
        "Vector database",
        "LLM provider"
      ],
      "deployments": [
        "docker",
        "local",
        "cloud"
      ],
      "difficulty": "intermediate",
      "cloudflare_ready": false,
      "use_cases": [
        "evaluate LLM outputs",
        "benchmark prompts and agents",
        "track model quality"
      ],
      "not_good_for": [
        "edge-only Cloudflare Workers deployment without adaptation"
      ],
      "classification": {
        "category": {
          "confidence": "high",
          "evidence": [
            "Matched \"eval\" in metadata.",
            "Matched \"evaluation\" in metadata."
          ]
        },
        "deployment": {
          "confidence": "medium",
          "evidence": [
            "Local usage is assumed for open source repositories unless contradicted."
          ]
        },
        "difficulty": {
          "confidence": "medium",
          "evidence": [
            "No strong beginner or advanced signal found; defaulting to intermediate."
          ]
        },
        "cloudflare_ready": {
          "confidence": "high",
          "evidence": [
            "Runtime blocker: python.",
            "No Cloudflare deployment signal detected.",
            "No wrangler.toml found in inspected repository files."
          ]
        }
      },
      "quality_signals": {
        "stars": 11983,
        "recent_commits": 53,
        "contributors": 52,
        "issue_response_time_hours": null,
        "release_frequency_180d": 6
      },
      "quality_signal_confidence": {
        "stars_30d_delta": "snapshot",
        "stars30d_window_days": 33,
        "commits_30d": "complete",
        "releases_180d": "complete",
        "contributors_90d": "complete"
      },
      "quality_score": 30,
      "agent_score": 78,
      "score": 89,
      "agent_score_breakdown": {
        "documentation": 90,
        "maintenance": 50,
        "deployment": 80,
        "popularity": 82,
        "community": 97
      },
      "git_top_score": 89,
      "git_top_score_breakdown": {
        "community": 100,
        "maintenance": 66,
        "documentation": 84,
        "stability": 90,
        "adoption": 100,
        "agent_readability": 100
      },
      "verification": {
        "schema_version": "git-top.verification.v1",
        "overall_status": "partial",
        "observed_at": "2026-09-20T05:31:07.686Z",
        "signals": {
          "activity": {
            "status": "observed",
            "source": "github_metadata",
            "evidence": [
              "project.pushed_at",
              "metrics.recent_push_days"
            ]
          },
          "license": {
            "status": "observed",
            "source": "github_metadata",
            "evidence": [
              "project.license"
            ]
          },
          "documentation": {
            "status": "observed",
            "source": "github_metadata",
            "evidence": [
              "project.description"
            ]
          },
          "runtime": {
            "status": "inferred",
            "source": "git_top_heuristic",
            "evidence": [
              "agent_card.deployment",
              "agent_card.cloudflare_ready"
            ]
          },
          "install": {
            "status": "not_run",
            "source": "git_top_runtime",
            "evidence": [
              "installation/build probe is not enabled"
            ]
          },
          "security": {
            "status": "not_run",
            "source": "git_top_runtime",
            "evidence": [
              "dependency/security scan is not enabled"
            ]
          },
          "mcp": {
            "status": "not_applicable",
            "source": "git_top_runtime",
            "evidence": [
              "project is not classified as mcp_server"
            ]
          }
        },
        "coverage": {
          "observed": 3,
          "inferred": 1,
          "not_run": 2,
          "unknown": 0
        },
        "next_steps": [
          "Run an installation/build probe before production adoption.",
          "Run a dependency and security scan before treating the score as a trust claim."
        ]
      },
      "summary": {
        "tl_dr": "Use dataelement/bisheng when the user needs a llm eval project with docker, local, cloud deployment options.",
        "purpose": "Use dataelement/bisheng when the user needs a llm eval project with docker, local, cloud deployment options.",
        "install": "Run with Docker using the repository's container instructions.",
        "inputs": [
          "prompts",
          "model outputs",
          "test cases"
        ],
        "outputs": [
          "scores",
          "benchmarks",
          "eval reports"
        ],
        "good_for": [
          "evaluate LLM outputs",
          "benchmark prompts and agents",
          "track model quality",
          "model evaluation",
          "benchmarking",
          "regression testing"
        ],
        "not_good_for": [
          "edge-only Cloudflare Workers deployment without adaptation",
          "production inference serving",
          "end-user chat apps"
        ],
        "deployment": [
          "docker",
          "local",
          "cloud"
        ],
        "alternatives": [
          {
            "repo": "promptfoo/promptfoo",
            "reason": "Same llm eval intent with rag overlap."
          },
          {
            "repo": "comet-ml/opik",
            "reason": "Same llm eval intent with rag, observability, workflow overlap."
          },
          {
            "repo": "modelscope/evalscope",
            "reason": "Same llm eval intent with rag overlap."
          }
        ]
      },
      "evidence": {
        "classification": {
          "category": {
            "confidence": "high",
            "evidence": [
              "Matched \"eval\" in metadata.",
              "Matched \"evaluation\" in metadata."
            ]
          },
          "deployment": {
            "confidence": "medium",
            "evidence": [
              "Local usage is assumed for open source repositories unless contradicted."
            ]
          },
          "difficulty": {
            "confidence": "medium",
            "evidence": [
              "No strong beginner or advanced signal found; defaulting to intermediate."
            ]
          },
          "cloudflare_ready": {
            "confidence": "high",
            "evidence": [
              "Runtime blocker: python.",
              "No Cloudflare deployment signal detected.",
              "No wrangler.toml found in inspected repository files."
            ]
          }
        },
        "quality_signal_confidence": {
          "stars_30d_delta": "snapshot",
          "stars30d_window_days": 33,
          "commits_30d": "complete",
          "releases_180d": "complete",
          "contributors_90d": "complete"
        },
        "verification": {
          "schema_version": "git-top.verification.v1",
          "overall_status": "partial",
          "observed_at": "2026-09-20T05:31:07.686Z",
          "signals": {
            "activity": {
              "status": "observed",
              "source": "github_metadata",
              "evidence": [
                "project.pushed_at",
                "metrics.recent_push_days"
              ]
            },
            "license": {
              "status": "observed",
              "source": "github_metadata",
              "evidence": [
                "project.license"
              ]
            },
            "documentation": {
              "status": "observed",
              "source": "github_metadata",
              "evidence": [
                "project.description"
              ]
            },
            "runtime": {
              "status": "inferred",
              "source": "git_top_heuristic",
              "evidence": [
                "agent_card.deployment",
                "agent_card.cloudflare_ready"
              ]
            },
            "install": {
              "status": "not_run",
              "source": "git_top_runtime",
              "evidence": [
                "installation/build probe is not enabled"
              ]
            },
            "security": {
              "status": "not_run",
              "source": "git_top_runtime",
              "evidence": [
                "dependency/security scan is not enabled"
              ]
            },
            "mcp": {
              "status": "not_applicable",
              "source": "git_top_runtime",
              "evidence": [
                "project is not classified as mcp_server"
              ]
            }
          },
          "coverage": {
            "observed": 3,
            "inferred": 1,
            "not_run": 2,
            "unknown": 0
          },
          "next_steps": [
            "Run an installation/build probe before production adoption.",
            "Run a dependency and security scan before treating the score as a trust claim."
          ]
        },
        "source_fields": [
          "project.description",
          "project.topics",
          "project.language",
          "project.license",
          "agent_card.summary_for_agent",
          "agent_card.use_cases",
          "agent_card.deployment",
          "agent_card.classification",
          "metrics",
          "verification.signals"
        ],
        "caveats": [
          "edge-only Cloudflare Workers deployment without adaptation",
          "Independent installation, security, or runtime probes have not been run for this project."
        ],
        "confidence_reason": "Evidence is usable for comparison, but agents should cite caveats before making a strong recommendation.",
        "last_verified_at": "2026-09-20T05:31:07.686Z"
      },
      "caveats": [
        "edge-only Cloudflare Workers deployment without adaptation",
        "Independent installation, security, or runtime probes have not been run for this project."
      ],
      "confidence_reason": "Evidence is usable for comparison, but agents should cite caveats before making a strong recommendation.",
      "source_fields": [
        "project.description",
        "project.topics",
        "project.language",
        "project.license",
        "agent_card.summary_for_agent",
        "agent_card.use_cases",
        "agent_card.deployment",
        "agent_card.classification",
        "metrics",
        "verification.signals"
      ],
      "last_verified_at": "2026-09-20T05:31:07.686Z"
    },
    {
      "project_id": "modelscope/evalscope",
      "repo": "modelscope/evalscope",
      "name": "evalscope",
      "github_url": "https://github.com/modelscope/evalscope",
      "homepage_url": "https://modelscope.github.io/evalscope/",
      "language": "Python",
      "license": "Apache-2.0",
      "project_kind": "project",
      "category": [
        "llm_eval"
      ],
      "tags": [
        "evaluation",
        "llm",
        "performance",
        "rag",
        "vlm"
      ],
      "description": "A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.",
      "overview": "Use modelscope/evalscope when the user needs a llm eval project with docker, library-only, local deployment options.",
      "alternatives": [
        {
          "repo": "promptfoo/promptfoo",
          "reason": "Same llm eval intent with rag overlap."
        },
        {
          "repo": "comet-ml/opik",
          "reason": "Same llm eval intent with rag overlap."
        },
        {
          "repo": "IntelLabs/RAG-FiT",
          "reason": "Same llm eval intent with rag overlap."
        }
      ],
      "related": [],
      "dependencies": [
        "Vector database",
        "LLM provider"
      ],
      "deployments": [
        "docker",
        "library_only",
        "local",
        "cloud"
      ],
      "difficulty": "beginner",
      "cloudflare_ready": false,
      "use_cases": [
        "evaluate LLM outputs",
        "benchmark prompts and agents",
        "track model quality"
      ],
      "not_good_for": [
        "edge-only Cloudflare Workers deployment without adaptation",
        "users expecting a complete hosted product"
      ],
      "classification": {
        "category": {
          "confidence": "high",
          "evidence": [
            "Matched \"eval\" in metadata.",
            "Matched \"evaluation\" in metadata.",
            "Matched \"benchmark\" in metadata."
          ]
        },
        "deployment": {
          "confidence": "high",
          "evidence": [
            "Matched \"pip install\" in repository content.",
            "Local usage is assumed for open source repositories unless contradicted."
          ]
        },
        "difficulty": {
          "confidence": "medium",
          "evidence": [
            "Repository has under 10k stars, so complexity is treated conservatively."
          ]
        },
        "cloudflare_ready": {
          "confidence": "high",
          "evidence": [
            "Runtime blocker: python, gpu.",
            "No Cloudflare deployment signal detected.",
            "No wrangler.toml found in inspected repository files."
          ]
        }
      },
      "quality_signals": {
        "stars": 3449,
        "recent_commits": 96,
        "contributors": 100,
        "issue_response_time_hours": null,
        "release_frequency_180d": 13
      },
      "quality_signal_confidence": {
        "stars_30d_delta": "snapshot",
        "stars30d_window_days": 34,
        "commits_30d": "complete",
        "releases_180d": "complete",
        "contributors_90d": "partial"
      },
      "quality_score": 49,
      "agent_score": 85,
      "score": 94,
      "agent_score_breakdown": {
        "documentation": 90,
        "maintenance": 75,
        "deployment": 90,
        "popularity": 71,
        "community": 100
      },
      "git_top_score": 94,
      "git_top_score_breakdown": {
        "community": 100,
        "maintenance": 83,
        "documentation": 84,
        "stability": 100,
        "adoption": 100,
        "agent_readability": 100
      },
      "verification": {
        "schema_version": "git-top.verification.v1",
        "overall_status": "partial",
        "observed_at": "2026-09-20T12:01:00.470Z",
        "signals": {
          "activity": {
            "status": "observed",
            "source": "github_metadata",
            "evidence": [
              "project.pushed_at",
              "metrics.recent_push_days"
            ]
          },
          "license": {
            "status": "observed",
            "source": "github_metadata",
            "evidence": [
              "project.license"
            ]
          },
          "documentation": {
            "status": "observed",
            "source": "github_metadata",
            "evidence": [
              "project.description"
            ]
          },
          "runtime": {
            "status": "inferred",
            "source": "git_top_heuristic",
            "evidence": [
              "agent_card.deployment",
              "agent_card.cloudflare_ready"
            ]
          },
          "install": {
            "status": "not_run",
            "source": "git_top_runtime",
            "evidence": [
              "installation/build probe is not enabled"
            ]
          },
          "security": {
            "status": "not_run",
            "source": "git_top_runtime",
            "evidence": [
              "dependency/security scan is not enabled"
            ]
          },
          "mcp": {
            "status": "not_applicable",
            "source": "git_top_runtime",
            "evidence": [
              "project is not classified as mcp_server"
            ]
          }
        },
        "coverage": {
          "observed": 3,
          "inferred": 1,
          "not_run": 2,
          "unknown": 0
        },
        "next_steps": [
          "Run an installation/build probe before production adoption.",
          "Run a dependency and security scan before treating the score as a trust claim."
        ]
      },
      "summary": {
        "tl_dr": "Use modelscope/evalscope when the user needs a llm eval project with docker, library-only, local deployment options.",
        "purpose": "Use modelscope/evalscope when the user needs a llm eval project with docker, library-only, local deployment options.",
        "install": "Run with Docker using the repository's container instructions.",
        "inputs": [
          "prompts",
          "model outputs",
          "test cases"
        ],
        "outputs": [
          "scores",
          "benchmarks",
          "eval reports"
        ],
        "good_for": [
          "evaluate LLM outputs",
          "benchmark prompts and agents",
          "track model quality",
          "model evaluation",
          "benchmarking",
          "regression testing"
        ],
        "not_good_for": [
          "edge-only Cloudflare Workers deployment without adaptation",
          "users expecting a complete hosted product",
          "production inference serving",
          "end-user chat apps"
        ],
        "deployment": [
          "docker",
          "library_only",
          "local",
          "cloud"
        ],
        "alternatives": [
          {
            "repo": "promptfoo/promptfoo",
            "reason": "Same llm eval intent with rag overlap."
          },
          {
            "repo": "comet-ml/opik",
            "reason": "Same llm eval intent with rag overlap."
          },
          {
            "repo": "IntelLabs/RAG-FiT",
            "reason": "Same llm eval intent with rag overlap."
          }
        ]
      },
      "evidence": {
        "classification": {
          "category": {
            "confidence": "high",
            "evidence": [
              "Matched \"eval\" in metadata.",
              "Matched \"evaluation\" in metadata.",
              "Matched \"benchmark\" in metadata."
            ]
          },
          "deployment": {
            "confidence": "high",
            "evidence": [
              "Matched \"pip install\" in repository content.",
              "Local usage is assumed for open source repositories unless contradicted."
            ]
          },
          "difficulty": {
            "confidence": "medium",
            "evidence": [
              "Repository has under 10k stars, so complexity is treated conservatively."
            ]
          },
          "cloudflare_ready": {
            "confidence": "high",
            "evidence": [
              "Runtime blocker: python, gpu.",
              "No Cloudflare deployment signal detected.",
              "No wrangler.toml found in inspected repository files."
            ]
          }
        },
        "quality_signal_confidence": {
          "stars_30d_delta": "snapshot",
          "stars30d_window_days": 34,
          "commits_30d": "complete",
          "releases_180d": "complete",
          "contributors_90d": "partial"
        },
        "verification": {
          "schema_version": "git-top.verification.v1",
          "overall_status": "partial",
          "observed_at": "2026-09-20T12:01:00.470Z",
          "signals": {
            "activity": {
              "status": "observed",
              "source": "github_metadata",
              "evidence": [
                "project.pushed_at",
                "metrics.recent_push_days"
              ]
            },
            "license": {
              "status": "observed",
              "source": "github_metadata",
              "evidence": [
                "project.license"
              ]
            },
            "documentation": {
              "status": "observed",
              "source": "github_metadata",
              "evidence": [
                "project.description"
              ]
            },
            "runtime": {
              "status": "inferred",
              "source": "git_top_heuristic",
              "evidence": [
                "agent_card.deployment",
                "agent_card.cloudflare_ready"
              ]
            },
            "install": {
              "status": "not_run",
              "source": "git_top_runtime",
              "evidence": [
                "installation/build probe is not enabled"
              ]
            },
            "security": {
              "status": "not_run",
              "source": "git_top_runtime",
              "evidence": [
                "dependency/security scan is not enabled"
              ]
            },
            "mcp": {
              "status": "not_applicable",
              "source": "git_top_runtime",
              "evidence": [
                "project is not classified as mcp_server"
              ]
            }
          },
          "coverage": {
            "observed": 3,
            "inferred": 1,
            "not_run": 2,
            "unknown": 0
          },
          "next_steps": [
            "Run an installation/build probe before production adoption.",
            "Run a dependency and security scan before treating the score as a trust claim."
          ]
        },
        "source_fields": [
          "project.description",
          "project.topics",
          "project.language",
          "project.license",
          "agent_card.summary_for_agent",
          "agent_card.use_cases",
          "agent_card.deployment",
          "agent_card.classification",
          "metrics",
          "verification.signals"
        ],
        "caveats": [
          "edge-only Cloudflare Workers deployment without adaptation",
          "users expecting a complete hosted product",
          "Partial or estimated quality signals: contributors90d.",
          "Independent installation, security, or runtime probes have not been run for this project."
        ],
        "confidence_reason": "Classification evidence and quality signals are strong enough for shortlist reasoning when metadata is current.",
        "last_verified_at": "2026-09-20T12:01:00.470Z"
      },
      "caveats": [
        "edge-only Cloudflare Workers deployment without adaptation",
        "users expecting a complete hosted product",
        "Partial or estimated quality signals: contributors90d.",
        "Independent installation, security, or runtime probes have not been run for this project."
      ],
      "confidence_reason": "Classification evidence and quality signals are strong enough for shortlist reasoning when metadata is current.",
      "source_fields": [
        "project.description",
        "project.topics",
        "project.language",
        "project.license",
        "agent_card.summary_for_agent",
        "agent_card.use_cases",
        "agent_card.deployment",
        "agent_card.classification",
        "metrics",
        "verification.signals"
      ],
      "last_verified_at": "2026-09-20T12:01:00.470Z"
    },
    {
      "project_id": "Purewhiter/mobilegym",
      "repo": "Purewhiter/mobilegym",
      "name": "mobilegym",
      "github_url": "https://github.com/Purewhiter/mobilegym",
      "homepage_url": "https://mobilegym.dev",
      "language": "Python",
      "license": "Apache-2.0",
      "project_kind": "project",
      "category": [
        "llm_eval"
      ],
      "tags": [
        "agent",
        "agents",
        "ai",
        "android",
        "automation",
        "benchmark",
        "gym",
        "llm",
        "llm-agents",
        "mobile-agent",
        "online-rl",
        "react",
        "reinforcement-learning",
        "rl",
        "rl-environment",
        "sim-to-real",
        "simulator",
        "typescript",
        "vlm"
      ],
      "description": "[EMNLP 2026] MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research · 浏览器里运行的安卓模拟器 · Browser-hosted Android Simulator · Verifiable Evaluation · Scalable Online RL Training",
      "overview": "Use Purewhiter/mobilegym when the user needs a llm eval project with library-only, local, cloud deployment options.",
      "alternatives": [
        {
          "repo": "comet-ml/opik",
          "reason": "Same llm eval intent with workflow overlap."
        },
        {
          "repo": "modelscope/evalscope",
          "reason": "Similar llm eval with library_only/local deployment overlap."
        },
        {
          "repo": "dataelement/bisheng",
          "reason": "Same llm eval intent with workflow overlap."
        }
      ],
      "related": [],
      "dependencies": [
        "Browser automation",
        "LLM provider"
      ],
      "deployments": [
        "library_only",
        "local",
        "cloud"
      ],
      "difficulty": "beginner",
      "cloudflare_ready": false,
      "use_cases": [
        "evaluate LLM outputs",
        "benchmark prompts and agents",
        "track model quality"
      ],
      "not_good_for": [
        "edge-only Cloudflare Workers deployment without adaptation",
        "users expecting a complete hosted product"
      ],
      "classification": {
        "category": {
          "confidence": "high",
          "evidence": [
            "Matched \"eval\" in metadata.",
            "Matched \"evaluation\" in metadata.",
            "Matched \"benchmark\" in metadata."
          ]
        },
        "deployment": {
          "confidence": "high",
          "evidence": [
            "Matched \"pip install\" in repository content.",
            "Matched \"npm install\" in repository content.",
            "Local usage is assumed for open source repositories unless contradicted."
          ]
        },
        "difficulty": {
          "confidence": "medium",
          "evidence": [
            "Repository has under 10k stars, so complexity is treated conservatively."
          ]
        },
        "cloudflare_ready": {
          "confidence": "high",
          "evidence": [
            "Runtime blocker: python.",
            "No Cloudflare deployment signal detected.",
            "No wrangler.toml found in inspected repository files."
          ]
        }
      },
      "quality_signals": {
        "stars": 800,
        "recent_commits": 15,
        "contributors": 6,
        "issue_response_time_hours": null,
        "release_frequency_180d": 2
      },
      "quality_signal_confidence": {
        "stars_30d_delta": "snapshot",
        "stars30d_window_days": 34,
        "commits_30d": "complete",
        "releases_180d": "complete",
        "contributors_90d": "complete"
      },
      "quality_score": 10,
      "agent_score": 60,
      "score": 77,
      "agent_score_breakdown": {
        "documentation": 90,
        "maintenance": 23,
        "deployment": 80,
        "popularity": 58,
        "community": 51
      },
      "git_top_score": 77,
      "git_top_score_breakdown": {
        "community": 89,
        "maintenance": 31,
        "documentation": 84,
        "stability": 86,
        "adoption": 85,
        "agent_readability": 100
      },
      "verification": {
        "schema_version": "git-top.verification.v1",
        "overall_status": "partial",
        "observed_at": "2026-09-25T00:31:06.358Z",
        "signals": {
          "activity": {
            "status": "observed",
            "source": "github_metadata",
            "evidence": [
              "project.pushed_at",
              "metrics.recent_push_days"
            ]
          },
          "license": {
            "status": "observed",
            "source": "github_metadata",
            "evidence": [
              "project.license"
            ]
          },
          "documentation": {
            "status": "observed",
            "source": "github_metadata",
            "evidence": [
              "project.description"
            ]
          },
          "runtime": {
            "status": "inferred",
            "source": "git_top_heuristic",
            "evidence": [
              "agent_card.deployment",
              "agent_card.cloudflare_ready"
            ]
          },
          "install": {
            "status": "not_run",
            "source": "git_top_runtime",
            "evidence": [
              "installation/build probe is not enabled"
            ]
          },
          "security": {
            "status": "not_run",
            "source": "git_top_runtime",
            "evidence": [
              "dependency/security scan is not enabled"
            ]
          },
          "mcp": {
            "status": "not_applicable",
            "source": "git_top_runtime",
            "evidence": [
              "project is not classified as mcp_server"
            ]
          }
        },
        "coverage": {
          "observed": 3,
          "inferred": 1,
          "not_run": 2,
          "unknown": 0
        },
        "next_steps": [
          "Run an installation/build probe before production adoption.",
          "Run a dependency and security scan before treating the score as a trust claim."
        ]
      },
      "summary": {
        "tl_dr": "Use Purewhiter/mobilegym when the user needs a llm eval project with library-only, local, cloud deployment options.",
        "purpose": "Use Purewhiter/mobilegym when the user needs a llm eval project with library-only, local, cloud deployment options.",
        "install": "Install as a library or package using the repository instructions.",
        "inputs": [
          "prompts",
          "model outputs",
          "test cases"
        ],
        "outputs": [
          "scores",
          "benchmarks",
          "eval reports"
        ],
        "good_for": [
          "evaluate LLM outputs",
          "benchmark prompts and agents",
          "track model quality",
          "model evaluation",
          "benchmarking",
          "regression testing"
        ],
        "not_good_for": [
          "edge-only Cloudflare Workers deployment without adaptation",
          "users expecting a complete hosted product",
          "production inference serving",
          "end-user chat apps"
        ],
        "deployment": [
          "library_only",
          "local",
          "cloud"
        ],
        "alternatives": [
          {
            "repo": "comet-ml/opik",
            "reason": "Same llm eval intent with workflow overlap."
          },
          {
            "repo": "modelscope/evalscope",
            "reason": "Similar llm eval with library_only/local deployment overlap."
          },
          {
            "repo": "dataelement/bisheng",
            "reason": "Same llm eval intent with workflow overlap."
          }
        ]
      },
      "evidence": {
        "classification": {
          "category": {
            "confidence": "high",
            "evidence": [
              "Matched \"eval\" in metadata.",
              "Matched \"evaluation\" in metadata.",
              "Matched \"benchmark\" in metadata."
            ]
          },
          "deployment": {
            "confidence": "high",
            "evidence": [
              "Matched \"pip install\" in repository content.",
              "Matched \"npm install\" in repository content.",
              "Local usage is assumed for open source repositories unless contradicted."
            ]
          },
          "difficulty": {
            "confidence": "medium",
            "evidence": [
              "Repository has under 10k stars, so complexity is treated conservatively."
            ]
          },
          "cloudflare_ready": {
            "confidence": "high",
            "evidence": [
              "Runtime blocker: python.",
              "No Cloudflare deployment signal detected.",
              "No wrangler.toml found in inspected repository files."
            ]
          }
        },
        "quality_signal_confidence": {
          "stars_30d_delta": "snapshot",
          "stars30d_window_days": 34,
          "commits_30d": "complete",
          "releases_180d": "complete",
          "contributors_90d": "complete"
        },
        "verification": {
          "schema_version": "git-top.verification.v1",
          "overall_status": "partial",
          "observed_at": "2026-09-25T00:31:06.358Z",
          "signals": {
            "activity": {
              "status": "observed",
              "source": "github_metadata",
              "evidence": [
                "project.pushed_at",
                "metrics.recent_push_days"
              ]
            },
            "license": {
              "status": "observed",
              "source": "github_metadata",
              "evidence": [
                "project.license"
              ]
            },
            "documentation": {
              "status": "observed",
              "source": "github_metadata",
              "evidence": [
                "project.description"
              ]
            },
            "runtime": {
              "status": "inferred",
              "source": "git_top_heuristic",
              "evidence": [
                "agent_card.deployment",
                "agent_card.cloudflare_ready"
              ]
            },
            "install": {
              "status": "not_run",
              "source": "git_top_runtime",
              "evidence": [
                "installation/build probe is not enabled"
              ]
            },
            "security": {
              "status": "not_run",
              "source": "git_top_runtime",
              "evidence": [
                "dependency/security scan is not enabled"
              ]
            },
            "mcp": {
              "status": "not_applicable",
              "source": "git_top_runtime",
              "evidence": [
                "project is not classified as mcp_server"
              ]
            }
          },
          "coverage": {
            "observed": 3,
            "inferred": 1,
            "not_run": 2,
            "unknown": 0
          },
          "next_steps": [
            "Run an installation/build probe before production adoption.",
            "Run a dependency and security scan before treating the score as a trust claim."
          ]
        },
        "source_fields": [
          "project.description",
          "project.topics",
          "project.language",
          "project.license",
          "agent_card.summary_for_agent",
          "agent_card.use_cases",
          "agent_card.deployment",
          "agent_card.classification",
          "metrics",
          "verification.signals"
        ],
        "caveats": [
          "edge-only Cloudflare Workers deployment without adaptation",
          "users expecting a complete hosted product",
          "Independent installation, security, or runtime probes have not been run for this project."
        ],
        "confidence_reason": "Classification evidence and quality signals are strong enough for shortlist reasoning when metadata is current.",
        "last_verified_at": "2026-09-25T00:31:06.358Z"
      },
      "caveats": [
        "edge-only Cloudflare Workers deployment without adaptation",
        "users expecting a complete hosted product",
        "Independent installation, security, or runtime probes have not been run for this project."
      ],
      "confidence_reason": "Classification evidence and quality signals are strong enough for shortlist reasoning when metadata is current.",
      "source_fields": [
        "project.description",
        "project.topics",
        "project.language",
        "project.license",
        "agent_card.summary_for_agent",
        "agent_card.use_cases",
        "agent_card.deployment",
        "agent_card.classification",
        "metrics",
        "verification.signals"
      ],
      "last_verified_at": "2026-09-25T00:31:06.358Z"
    }
  ],
  "resolved_from": {
    "requested_id": "agentevals-dev/agentevals",
    "resolved_id": "agentevals-dev/agentevals",
    "resolution": "direct"
  },
  "metadata": {
    "source": "d1",
    "reason": "d1_query",
    "project_count": 1213,
    "generated_at": "2026-09-26T19:32:12.166Z",
    "snapshot_id": "d1:1213:2026-09-26T19:31:09.378Z",
    "latest_synced_at": "2026-09-26T19:31:09.378Z",
    "schema_version": "git-top.knowledge.v1",
    "loaded_project_limit": 2000,
    "truncated": false
  }
}