opendatalab / MinerU

{
  "data": {
    "repo": {
      "topics": [
        "ai4science",
        "document-analysis",
        "docx",
        "extract-data",
        "layout-analysis",
        "ocr",
        "parser",
        "pdf",
        "pdf-converter",
        "pdf-extractor-llm",
        "pdf-extractor-pretrain",
        "pdf-extractor-rag",
        "pdf-parser",
        "pptx",
        "python",
        "xlsx"
      ],
      "is_fork": false,
      "size_kb": 157783,
      "has_wiki": false,
      "homepage": "https://opendatalab.github.io/MinerU/",
      "languages": {
        "Python": 2590937,
        "Dockerfile": 16927
      },
      "pushed_at": "2026-07-10T11:51:50Z",
      "created_at": "2024-02-29T08:52:34Z",
      "owner_type": "Organization",
      "updated_at": "2026-07-13T01:10:58Z",
      "description": "Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.",
      "is_archived": false,
      "is_disabled": false,
      "license_spdx": null,
      "default_branch": "master",
      "primary_language": "Python"
    },
    "owner": {
      "blog": "https://opendatalab.org.cn",
      "name": "OpenDataLab",
      "type": "Organization",
      "login": "opendatalab",
      "company": null,
      "location": "China",
      "followers": 2906,
      "avatar_url": "https://avatars.githubusercontent.com/u/97503431?v=4",
      "created_at": "2022-01-11T06:43:49Z",
      "is_verified": null,
      "public_repos": 67,
      "account_age_days": 1643
    },
    "activity": {
      "releases_count": 100,
      "commits_last_year": 2382,
      "latest_release_at": "2026-07-10T11:54:35Z",
      "latest_release_tag": "mineru-3.4.4-released",
      "days_since_last_push": 2,
      "active_weeks_last_year": 50,
      "days_since_latest_release": 2,
      "mean_days_between_releases": 4.8
    },
    "community": {
      "has_readme": true,
      "has_license": true,
      "has_description": true,
      "has_contributing": false,
      "health_percentage": 75,
      "has_issue_template": false,
      "has_code_of_conduct": false,
      "has_pull_request_template": true
    },
    "ecosystem": {
      "packages": [
        {
          "name": "mineru",
          "exists": true,
          "license": "LicenseRef-MinerU-Open-Source-License",
          "ecosystem": "pypi",
          "matches_repo": true,
          "registry_url": "https://pypi.org/project/mineru/",
          "is_deprecated": false,
          "latest_version": "3.4.4",
          "repository_url": "https://github.com/opendatalab/MinerU",
          "versions_count": 78,
          "total_downloads": null,
          "dependents_count": null,
          "deprecation_note": null,
          "maintainers_count": null,
          "monthly_downloads": 344012,
          "first_published_at": "2025-06-13T12:59:53.563001Z",
          "latest_published_at": "2026-07-10T11:54:43.539903Z",
          "latest_version_yanked": null,
          "days_since_latest_publish": 2
        }
      ]
    },
    "popularity": {
      "forks": 6245,
      "stars": 74362,
      "watchers": 272,
      "open_issues_and_prs": 31
    },
    "ai_readiness": {
      "has_nix": false,
      "example_dirs": [],
      "has_llms_txt": false,
      "has_dockerfile": true,
      "has_mcp_signal": false,
      "bootstrap_files": [],
      "api_schema_files": [],
      "has_devcontainer": false,
      "typecheck_configs": [],
      "largest_source_bytes": 140821,
      "source_files_sampled": 222,
      "oversized_source_files": 8,
      "agent_instruction_files": [],
      "agent_instruction_max_bytes": null
    },
    "dependencies": {
      "manifests": [
        "docs/requirements.txt",
        "pyproject.toml"
      ],
      "ecosystems": [
        "pypi"
      ],
      "dependencies": [
        {
          "name": "click",
          "manifest": "pyproject.toml",
          "ecosystem": "pypi",
          "version_constraint": ">=8.1.7"
        },
        {
          "name": "loguru",
          "manifest": "pyproject.toml",
          "ecosystem": "pypi",
          "version_constraint": ">=0.7.2"
        },
        {
          "name": "numpy",
          "manifest": "pyproject.toml",
          "ecosystem": "pypi",
          "version_constraint": ">=1.21.6"
        },
        {
          "name": "tqdm",
          "manifest": "pyproject.toml",
          "ecosystem": "pypi",
          "version_constraint": ">=4.67.1"
        },
        {
          "name": "requests",
          "manifest": "pyproject.toml",
          "ecosystem": "pypi",
          "version_constraint": null
        },
        {
          "name": "httpx",
          "manifest": "pyproject.toml",
          "ecosystem": "pypi",
          "version_constraint": null
        },
        {
          "name": "pillow",
          "manifest": "pyproject.toml",
          "ecosystem": "pypi",
          "version_constraint": ">=11.0.0"
        },
        {
          "name": "pypdfium2",
          "manifest": "pyproject.toml",
          "ecosystem": "pypi",
          "version_constraint": ">=4.30.0,<6.0.0"
        },
        {
          "name": "pypdf",
          "manifest": "pyproject.toml",
          "ecosystem": "pypi",
          "version_constraint": ">=5.6.0"
        },
        {
          "name": "reportlab",
          "manifest": "pyproject.toml",
          "ecosystem": "pypi",
          "version_constraint": null
        },
        {
          "name": "pdftext",
          "manifest": "pyproject.toml",
          "ecosystem": "pypi",
          "version_constraint": ">=0.6.3,<0.8.0"
        },
        {
          "name": "modelscope",
          "manifest": "pyproject.toml",
          "ecosystem": "pypi",
          "version_constraint": ">=1.26.0"
        },
        {
          "name": "huggingface-hub",
          "manifest": "pyproject.toml",
          "ecosystem": "pypi",
          "version_constraint": ">=0.32.4"
        },
        {
          "name": "json-repair",
          "manifest": "pyproject.toml",
          "ecosystem": "pypi",
          "version_constraint": ">=0.46.2"
        },
        {
          "name": "opencv-python",
          "manifest": "pyproject.toml",
          "ecosystem": "pypi",
          "version_constraint": ">=4.11.0.86"
        },
        {
          "name": "fast-langdetect",
          "manifest": "pyproject.toml",
          "ecosystem": "pypi",
          "version_constraint": ">=0.2.3,<0.3.0"
        },
        {
          "name": "openai",
          "manifest": "pyproject.toml",
          "ecosystem": "pypi",
          "version_constraint": ">=1.70.0,<3"
        },
        {
          "name": "beautifulsoup4",
          "manifest": "pyproject.toml",
          "ecosystem": "pypi",
          "version_constraint": ">=4.13.5,<5"
        },
        {
          "name": "magika",
          "manifest": "pyproject.toml",
          "ecosystem": "pypi",
          "version_constraint": ">=0.6.2,<1.1.0"
        },
        {
          "name": "mineru-vl-utils",
          "manifest": "pyproject.toml",
          "ecosystem": "pypi",
          "version_constraint": ">=1.0.5,<2"
        },
        {
          "name": "python-docx",
          "manifest": "pyproject.toml",
          "ecosystem": "pypi",
          "version_constraint": ">=1.2.0,<2"
        },
        {
          "name": "pypptx-with-oxml",
          "manifest": "pyproject.toml",
          "ecosystem": "pypi",
          "version_constraint": ">=1.0.3,<2"
        },
        {
          "name": "mammoth",
          "manifest": "pyproject.toml",
          "ecosystem": "pypi",
          "version_constraint": ">=1.11.0,<2"
        },
        {
          "name": "pylatexenc",
          "manifest": "pyproject.toml",
          "ecosystem": "pypi",
          "version_constraint": ">=2.10,<3"
        },
        {
          "name": "lxml",
          "manifest": "pyproject.toml",
          "ecosystem": "pypi",
          "version_constraint": ">=4.0.0,<7.0.0"
        },
        {
          "name": "openpyxl",
          "manifest": "pyproject.toml",
          "ecosystem": "pypi",
          "version_constraint": ">=3.1.5,<4"
        },
        {
          "name": "fastapi",
          "manifest": "pyproject.toml",
          "ecosystem": "pypi",
          "version_constraint": null
        },
        {
          "name": "python-multipart",
          "manifest": "pyproject.toml",
          "ecosystem": "pypi",
          "version_constraint": null
        },
        {
          "name": "uvicorn",
          "manifest": "pyproject.toml",
          "ecosystem": "pypi",
          "version_constraint": null
        }
      ]
    },
    "maintainership": {
      "issues": {
        "open_prs": 23,
        "merged_prs": 1530,
        "open_issues": 8,
        "closed_ratio": 0.996,
        "closed_issues": 2259,
        "closed_unmerged_prs": 195
      },
      "bus_factor": 1,
      "top_contributors": [
        {
          "type": "User",
          "login": "myhloli",
          "commits": 4709,
          "avatar_url": "https://avatars.githubusercontent.com/u/11393164?u=e9d5b4deeedaf4acb4c75c83a6d4863f206224da&v=4"
        },
        {
          "type": "User",
          "login": "Sidney233",
          "commits": 81,
          "avatar_url": "https://avatars.githubusercontent.com/u/54933042?u=055e9fcda7315edd1c5aa46953621e8039b821b5&v=4"
        },
        {
          "type": "User",
          "login": "dt-yy",
          "commits": 77,
          "avatar_url": "https://avatars.githubusercontent.com/u/102640628?u=40618aa9d1ef16aab63df0bd63e9edc4a794c452&v=4"
        },
        {
          "type": "Bot",
          "login": "github-actions[bot]",
          "commits": 48,
          "avatar_url": "https://avatars.githubusercontent.com/in/15368?v=4"
        },
        {
          "type": "User",
          "login": "Focusshang",
          "commits": 35,
          "avatar_url": "https://avatars.githubusercontent.com/u/25022954?u=14fd7c106d832967a11c684e51dec5c6e5ac7547&v=4"
        },
        {
          "type": "User",
          "login": "drunkpig",
          "commits": 32,
          "avatar_url": "https://avatars.githubusercontent.com/u/60862764?u=839436b67a8315ccb0606a918c486397db50dbba&v=4"
        },
        {
          "type": "User",
          "login": "papayalove",
          "commits": 25,
          "avatar_url": "https://avatars.githubusercontent.com/u/47357227?u=562355e992bb567c058af0a7a7a60ad7b72846fc&v=4"
        },
        {
          "type": "User",
          "login": "LollipopsAndWine",
          "commits": 25,
          "avatar_url": "https://avatars.githubusercontent.com/u/56671143?u=be4ec70485331500fae615cda881bfcdec2d0d96&v=4"
        },
        {
          "type": "User",
          "login": "icecraft",
          "commits": 13,
          "avatar_url": "https://avatars.githubusercontent.com/u/13513537?v=4"
        },
        {
          "type": "User",
          "login": "wangbinDL",
          "commits": 11,
          "avatar_url": "https://avatars.githubusercontent.com/u/69186975?u=e3721263b111f30e299389a66eb174691089298a&v=4"
        }
      ],
      "contributors_sampled": 73,
      "top_contributor_share": 0.909
    },
    "quality_signals": {
      "has_ci": true,
      "has_tests": true,
      "ci_workflows": [
        "cla.yml",
        "cli.yml",
        "mkdocs.yml",
        "python-package.yml",
        "rerun.yml"
      ],
      "has_docs_dir": true,
      "linter_configs": [],
      "has_editorconfig": false,
      "has_linter_config": false,
      "has_precommit_config": false
    },
    "security_signals": {
      "lockfiles": [],
      "scorecard": {
        "checks": [
          {
            "name": "Binary-Artifacts",
            "score": 10,
            "reason": "no binaries found in the repo",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#binary-artifacts"
          },
          {
            "name": "Branch-Protection",
            "score": 3,
            "reason": "branch protection is not maximal on development and all release branches",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#branch-protection"
          },
          {
            "name": "CI-Tests",
            "score": 10,
            "reason": "16 out of 16 merged PRs checked by a CI test -- score normalized to 10",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#ci-tests"
          },
          {
            "name": "CII-Best-Practices",
            "score": 0,
            "reason": "no effort to earn an OpenSSF best practices badge detected",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#cii-best-practices"
          },
          {
            "name": "Code-Review",
            "score": 0,
            "reason": "Found 0/19 approved changesets -- score normalized to 0",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#code-review"
          },
          {
            "name": "Contributors",
            "score": 10,
            "reason": "project has 7 contributing companies or organizations",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#contributors"
          },
          {
            "name": "Dangerous-Workflow",
            "score": 10,
            "reason": "no dangerous workflow patterns detected",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#dangerous-workflow"
          },
          {
            "name": "Dependency-Update-Tool",
            "score": 0,
            "reason": "no update tool detected",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#dependency-update-tool"
          },
          {
            "name": "Fuzzing",
            "score": 0,
            "reason": "project is not fuzzed",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#fuzzing"
          },
          {
            "name": "License",
            "score": 9,
            "reason": "license file detected",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#license"
          },
          {
            "name": "Maintained",
            "score": 10,
            "reason": "30 commit(s) and 16 issue activity found in the last 90 days -- score normalized to 10",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#maintained"
          },
          {
            "name": "Packaging",
            "score": null,
            "reason": "packaging workflow not detected",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#packaging"
          },
          {
            "name": "Pinned-Dependencies",
            "score": 0,
            "reason": "dependency not pinned by hash detected -- score normalized to 0",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#pinned-dependencies"
          },
          {
            "name": "SAST",
            "score": 0,
            "reason": "SAST tool is not run on all commits -- score normalized to 0",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#sast"
          },
          {
            "name": "Security-Policy",
            "score": 10,
            "reason": "security policy file detected",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#security-policy"
          },
          {
            "name": "Signed-Releases",
            "score": 0,
            "reason": "Project has not signed or included provenance with any releases.",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#signed-releases"
          },
          {
            "name": "Token-Permissions",
            "score": 0,
            "reason": "detected GitHub workflow tokens with excessive permissions",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#token-permissions"
          },
          {
            "name": "Vulnerabilities",
            "score": 10,
            "reason": "0 existing vulnerabilities detected",
            "documentation_url": "https://github.com/ossf/scorecard/blob/c395761df6afe1a69e476bc60a013a94bcbc153f/docs/checks.md#vulnerabilities"
          }
        ],
        "commit": "79d6d8d79fb8f3ddba5cc34c07a16f0ec36f56c7",
        "ran_at": "2026-07-13T01:19:56Z",
        "aggregate_score": 4.7,
        "scorecard_version": "v5.5.0"
      },
      "has_codeql_workflow": false,
      "has_security_policy": true,
      "has_dependabot_config": false
    }
  },
  "config": {
    "disabled_metrics": [],
    "disabled_categories": [],
    "disabled_components": {}
  },
  "source": {
    "url": "https://github.com/opendatalab/MinerU",
    "host": "github.com",
    "name": "MinerU",
    "owner": "opendatalab"
  },
  "metrics": {
    "overall": {
      "key": "overall",
      "band": "good",
      "name": "Overall health",
      "note": null,
      "notes": [],
      "value": 75,
      "inputs": {
        "security": 47,
        "vitality": 95,
        "community": 80,
        "governance": 69,
        "engineering": 77
      },
      "components": []
    },
    "categories": [
      {
        "key": "vitality",
        "band": "excellent",
        "name": "Vitality",
        "value": 95,
        "weight": 0.22,
        "metrics": [
          {
            "key": "development_activity",
            "band": "excellent",
            "name": "Development activity",
            "note": null,
            "notes": [],
            "value": 99,
            "inputs": {
              "commits_last_year": 2382,
              "human_commit_share": null,
              "days_since_last_push": 2,
              "active_weeks_last_year": 50
            },
            "components": [
              {
                "key": "push_recency",
                "name": "Push recency",
                "detail": "last push 2 days ago",
                "points": 36,
                "status": "met",
                "details": [
                  {
                    "code": "push_recency",
                    "params": {
                      "days": 2
                    }
                  }
                ],
                "max_points": 36
              },
              {
                "key": "commit_cadence",
                "name": "Commit cadence",
                "detail": "50/52 weeks with commits",
                "points": 34.6,
                "status": "partial",
                "details": [
                  {
                    "code": "commit_cadence_weeks",
                    "params": {
                      "weeks": 50
                    }
                  }
                ],
                "max_points": 36
              },
              {
                "key": "commit_volume",
                "name": "Commit volume",
                "detail": "2382 commits in the last year",
                "points": 18,
                "status": "met",
                "details": [
                  {
                    "code": "commits_last_year",
                    "params": {
                      "count": 2382
                    }
                  }
                ],
                "max_points": 18
              },
              {
                "key": "openssf_scorecard_maintained",
                "name": "OpenSSF Scorecard: Maintained",
                "detail": "30 commit(s) and 16 issue activity found in the last 90 days -- score normalized to 10",
                "points": 10,
                "status": "met",
                "details": [],
                "max_points": 10
              }
            ]
          },
          {
            "key": "release_discipline",
            "band": "excellent",
            "name": "Release discipline",
            "note": null,
            "notes": [],
            "value": 90,
            "inputs": {
              "releases_count": 100,
              "latest_release_tag": "mineru-3.4.4-released",
              "releases_from_tags": false,
              "days_since_latest_release": 2,
              "mean_days_between_releases": 4.8
            },
            "components": [
              {
                "key": "ships_releases",
                "name": "Ships releases",
                "detail": "100 releases published",
                "points": 27,
                "status": "met",
                "details": [
                  {
                    "code": "releases_published",
                    "params": {
                      "count": 100
                    }
                  }
                ],
                "max_points": 27
              },
              {
                "key": "release_recency",
                "name": "Release recency",
                "detail": "latest release 2 days ago",
                "points": 36,
                "status": "met",
                "details": [
                  {
                    "code": "release_recency",
                    "params": {
                      "days": 2
                    }
                  }
                ],
                "max_points": 36
              },
              {
                "key": "release_cadence",
                "name": "Release cadence",
                "detail": "a release every ~4.8 days",
                "points": 27,
                "status": "met",
                "details": [
                  {
                    "code": "release_cadence",
                    "params": {
                      "gap": 4.8
                    }
                  }
                ],
                "max_points": 27
              },
              {
                "key": "openssf_scorecard_signed_releases",
                "name": "OpenSSF Scorecard: Signed-Releases",
                "detail": "Project has not signed or included provenance with any releases.",
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 10
              }
            ]
          },
          {
            "key": "abandonment",
            "band": "excellent",
            "name": "Abandonment",
            "note": null,
            "notes": [],
            "value": 100,
            "inputs": {
              "cap": null,
              "state": "unverified",
              "guards": [],
              "signals": [],
              "red_flag": false,
              "multiplier_pct": 100,
              "declared_reason": null,
              "unverified_reason": "no_commit_sample",
              "unanswered_open_prs": null,
              "unanswered_open_issues": null,
              "days_since_last_merged_pr": null,
              "days_since_last_human_commit": null,
              "days_since_last_human_commit_is_floor": false
            },
            "components": [
              {
                "key": "project_is_still_maintained",
                "name": "Project is still maintained",
                "detail": "maintenance record not established from the collected data",
                "points": 100,
                "status": "met",
                "details": [
                  {
                    "code": "abandonment_unverified",
                    "params": {}
                  }
                ],
                "max_points": 100
              }
            ]
          }
        ],
        "description": "Is the project alive — is code being written and are releases shipping?"
      },
      {
        "key": "community",
        "band": "good",
        "name": "Community & Adoption",
        "value": 80,
        "weight": 0.18,
        "metrics": [
          {
            "key": "popularity",
            "band": "excellent",
            "name": "Popularity & adoption",
            "note": null,
            "notes": [],
            "value": 98,
            "inputs": {
              "forks": 6245,
              "stars": 74362,
              "watchers": 272,
              "growth_state": "unverified",
              "growth_factor_pct": 100,
              "growth_unverified_reason": "no_history"
            },
            "components": [
              {
                "key": "stars",
                "name": "Stars",
                "detail": "74,362 stars",
                "points": 60,
                "status": "met",
                "details": [
                  {
                    "code": "stars",
                    "params": {
                      "count": 74362
                    }
                  }
                ],
                "max_points": 60
              },
              {
                "key": "forks",
                "name": "Forks",
                "detail": "6,245 forks",
                "points": 25,
                "status": "met",
                "details": [
                  {
                    "code": "forks",
                    "params": {
                      "count": 6245
                    }
                  }
                ],
                "max_points": 25
              },
              {
                "key": "watchers",
                "name": "Watchers",
                "detail": "272 watchers",
                "points": 13.5,
                "status": "partial",
                "details": [
                  {
                    "code": "watchers",
                    "params": {
                      "count": 272
                    }
                  }
                ],
                "max_points": 15
              }
            ]
          },
          {
            "key": "community_health",
            "band": "moderate",
            "name": "Community health",
            "note": null,
            "notes": [],
            "value": 51,
            "inputs": {
              "has_readme": true,
              "has_license": true,
              "has_contributing": false,
              "has_issue_template": false,
              "has_code_of_conduct": false,
              "has_pull_request_template": true
            },
            "components": [
              {
                "key": "readme",
                "name": "README",
                "detail": null,
                "points": 22.5,
                "status": "met",
                "details": [],
                "max_points": 22.5
              },
              {
                "key": "license",
                "name": "License",
                "detail": "license file present, not a recognized license",
                "points": 16.9,
                "status": "partial",
                "details": [
                  {
                    "code": "license_custom",
                    "params": {}
                  }
                ],
                "max_points": 22.5
              },
              {
                "key": "contributing_guide",
                "name": "CONTRIBUTING guide",
                "detail": null,
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 18
              },
              {
                "key": "code_of_conduct",
                "name": "Code of conduct",
                "detail": null,
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 13.5
              },
              {
                "key": "issue_template",
                "name": "Issue template",
                "detail": null,
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 7.2
              },
              {
                "key": "pr_template",
                "name": "PR template",
                "detail": null,
                "points": 6.3,
                "status": "met",
                "details": [],
                "max_points": 6.3
              }
            ]
          },
          {
            "key": "ecosystem_adoption",
            "band": "excellent",
            "name": "Ecosystem adoption (downloads)",
            "note": "Excluded from scoring (no data or not applicable): Registry dependents. Remaining weights renormalized.",
            "notes": [
              {
                "code": "excluded_no_data",
                "params": {
                  "components": [
                    "registry_dependents"
                  ]
                }
              },
              {
                "code": "weights_renormalized",
                "params": {}
              }
            ],
            "value": 92,
            "inputs": {
              "packages": [
                "mineru"
              ],
              "dependents": null,
              "ecosystems": "pypi",
              "total_downloads": null,
              "monthly_downloads": 344012
            },
            "components": [
              {
                "key": "monthly_downloads",
                "name": "Monthly downloads",
                "detail": "344,012 downloads/month across pypi",
                "points": 73.8,
                "status": "partial",
                "details": [
                  {
                    "code": "downloads_monthly",
                    "params": {
                      "count": 344012,
                      "ecosystems": "pypi"
                    }
                  }
                ],
                "max_points": 80
              },
              {
                "key": "registry_dependents",
                "name": "Registry dependents",
                "detail": "not reported by this ecosystem",
                "points": 0,
                "status": "excluded",
                "details": [
                  {
                    "code": "not_reported_by_this_ecosystem",
                    "params": {}
                  }
                ],
                "max_points": 20
              }
            ]
          }
        ],
        "description": "Does the project have users, downloads, attention, and a welcoming setup for contributors?"
      },
      {
        "key": "governance",
        "band": "moderate",
        "name": "Sustainability & Governance",
        "value": 69,
        "weight": 0.24,
        "metrics": [
          {
            "key": "maintainer_resilience",
            "band": "at_risk",
            "name": "Maintainer resilience (bus factor)",
            "note": null,
            "notes": [],
            "value": 34,
            "inputs": {
              "bus_factor": 1,
              "contributors_sampled": 73,
              "top_contributor_share": 0.909
            },
            "components": [
              {
                "key": "bus_factor",
                "name": "Bus factor",
                "detail": "1 contributor(s) cover half of all commits",
                "points": 9,
                "status": "partial",
                "details": [
                  {
                    "code": "bus_factor",
                    "params": {
                      "count": 1
                    }
                  }
                ],
                "max_points": 54
              },
              {
                "key": "commit_distribution",
                "name": "Commit distribution",
                "detail": "top contributor authored 91% of commits",
                "points": 2,
                "status": "partial",
                "details": [
                  {
                    "code": "top_contributor_share",
                    "params": {
                      "share": 91
                    }
                  }
                ],
                "max_points": 22.5
              },
              {
                "key": "contributor_breadth",
                "name": "Contributor breadth",
                "detail": "73 contributors",
                "points": 13.5,
                "status": "met",
                "details": [
                  {
                    "code": "contributors_sampled",
                    "params": {
                      "count": 73
                    }
                  }
                ],
                "max_points": 13.5
              },
              {
                "key": "openssf_scorecard_contributors",
                "name": "OpenSSF Scorecard: Contributors",
                "detail": "project has 7 contributing companies or organizations",
                "points": 10,
                "status": "met",
                "details": [],
                "max_points": 10
              }
            ]
          },
          {
            "key": "responsiveness",
            "band": "good",
            "name": "Issue & PR responsiveness",
            "note": null,
            "notes": [],
            "value": 80,
            "inputs": {
              "merged_prs": 1530,
              "open_issues": 8,
              "closed_issues": 2259,
              "issue_closed_ratio": 0.996,
              "closed_unmerged_prs": 195
            },
            "components": [
              {
                "key": "issue_resolution",
                "name": "Issue resolution",
                "detail": "100% of issues closed",
                "points": 46.6,
                "status": "partial",
                "details": [
                  {
                    "code": "issues_closed_share",
                    "params": {
                      "share": 100
                    }
                  }
                ],
                "max_points": 46.75
              },
              {
                "key": "pr_acceptance",
                "name": "PR acceptance",
                "detail": "1530/1725 decided PRs merged",
                "points": 33.9,
                "status": "partial",
                "details": [
                  {
                    "code": "decided_prs_merged",
                    "params": {
                      "merged": 1530,
                      "decided": 1725
                    }
                  }
                ],
                "max_points": 38.25
              },
              {
                "key": "openssf_scorecard_code_review",
                "name": "OpenSSF Scorecard: Code-Review",
                "detail": "Found 0/19 approved changesets -- score normalized to 0",
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 15
              }
            ]
          },
          {
            "key": "stewardship",
            "band": "good",
            "name": "Ownership & stewardship",
            "note": null,
            "notes": [],
            "value": 77,
            "inputs": {
              "followers": 2906,
              "owner_type": "Organization",
              "is_verified": null,
              "owner_login": "opendatalab",
              "public_repos": 67,
              "account_age_days": 1643
            },
            "components": [
              {
                "key": "ownership_backing",
                "name": "Ownership backing",
                "detail": "organization-owned",
                "points": 30,
                "status": "met",
                "details": [
                  {
                    "code": "owner_organization",
                    "params": {}
                  }
                ],
                "max_points": 30
              },
              {
                "key": "verified_domain",
                "name": "Verified domain",
                "detail": null,
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 20
              },
              {
                "key": "owner_reach",
                "name": "Owner reach",
                "detail": "2,906 followers of opendatalab",
                "points": 24.9,
                "status": "partial",
                "details": [
                  {
                    "code": "owner_followers",
                    "params": {
                      "count": 2906,
                      "login": "opendatalab"
                    }
                  }
                ],
                "max_points": 25
              },
              {
                "key": "track_record",
                "name": "Track record",
                "detail": "67 public repos, account ~4 yr old",
                "points": 22,
                "status": "partial",
                "details": [
                  {
                    "code": "public_repos",
                    "params": {
                      "count": 67
                    }
                  },
                  {
                    "code": "account_age_years",
                    "params": {
                      "years": 4
                    }
                  }
                ],
                "max_points": 25
              }
            ]
          },
          {
            "key": "package_maintenance",
            "band": "excellent",
            "name": "Package maintenance",
            "note": null,
            "notes": [],
            "value": 100,
            "inputs": {
              "packages": [
                "mineru"
              ],
              "ecosystems": "pypi",
              "any_deprecated": false,
              "min_days_since_publish": 2
            },
            "components": [
              {
                "key": "published_resolvable",
                "name": "Published & resolvable",
                "detail": "1 package(s) on pypi",
                "points": 25,
                "status": "met",
                "details": [
                  {
                    "code": "packages_published",
                    "params": {
                      "count": 1,
                      "ecosystems": "pypi"
                    }
                  }
                ],
                "max_points": 25
              },
              {
                "key": "publish_recency",
                "name": "Publish recency",
                "detail": "latest publish 2 days ago",
                "points": 35,
                "status": "met",
                "details": [
                  {
                    "code": "publish_recency",
                    "params": {
                      "days": 2
                    }
                  }
                ],
                "max_points": 35
              },
              {
                "key": "version_history",
                "name": "Version history",
                "detail": "78 published versions",
                "points": 20,
                "status": "met",
                "details": [
                  {
                    "code": "published_versions",
                    "params": {
                      "count": 78
                    }
                  }
                ],
                "max_points": 20
              },
              {
                "key": "not_deprecated",
                "name": "Not deprecated",
                "detail": "active, not deprecated or yanked",
                "points": 20,
                "status": "met",
                "details": [
                  {
                    "code": "package_not_deprecated",
                    "params": {}
                  }
                ],
                "max_points": 20
              }
            ]
          }
        ],
        "description": "Will the project survive its people — bus factor, responsiveness, who backs it, and package upkeep?"
      },
      {
        "key": "engineering",
        "band": "good",
        "name": "Engineering Quality",
        "value": 77,
        "weight": 0.2,
        "metrics": [
          {
            "key": "engineering_practices",
            "band": "moderate",
            "name": "Engineering practices",
            "note": null,
            "notes": [],
            "value": 68,
            "inputs": {
              "has_ci": true,
              "has_tests": true,
              "has_editorconfig": false,
              "has_linter_config": false,
              "has_precommit_config": false
            },
            "components": [
              {
                "key": "ci_workflows",
                "name": "CI workflows",
                "detail": "5 workflow(s)",
                "points": 24,
                "status": "met",
                "details": [
                  {
                    "code": "ci_workflows",
                    "params": {
                      "count": 5
                    }
                  }
                ],
                "max_points": 24
              },
              {
                "key": "tests_present",
                "name": "Tests present",
                "detail": null,
                "points": 24,
                "status": "met",
                "details": [],
                "max_points": 24
              },
              {
                "key": "linter_config",
                "name": "Linter config",
                "detail": null,
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 16
              },
              {
                "key": "pre_commit_hooks",
                "name": "Pre-commit hooks",
                "detail": null,
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 9.6
              },
              {
                "key": "editorconfig",
                "name": ".editorconfig",
                "detail": null,
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 6.4
              },
              {
                "key": "openssf_scorecard_ci_tests",
                "name": "OpenSSF Scorecard: CI-Tests",
                "detail": "16 out of 16 merged PRs checked by a CI test -- score normalized to 10",
                "points": 20,
                "status": "met",
                "details": [],
                "max_points": 20
              }
            ]
          },
          {
            "key": "documentation",
            "band": "excellent",
            "name": "Documentation",
            "note": null,
            "notes": [],
            "value": 90,
            "inputs": {
              "topics": [
                "ai4science",
                "document-analysis",
                "docx",
                "extract-data",
                "layout-analysis",
                "ocr",
                "parser",
                "pdf",
                "pdf-converter",
                "pdf-extractor-llm",
                "pdf-extractor-pretrain",
                "pdf-extractor-rag",
                "pdf-parser",
                "pptx",
                "python",
                "xlsx"
              ],
              "has_wiki": false,
              "homepage": "https://opendatalab.github.io/MinerU/",
              "has_readme": true,
              "has_docs_dir": true,
              "has_description": true
            },
            "components": [
              {
                "key": "readme",
                "name": "README",
                "detail": null,
                "points": 30,
                "status": "met",
                "details": [],
                "max_points": 30
              },
              {
                "key": "documentation_directory",
                "name": "Documentation directory",
                "detail": null,
                "points": 25,
                "status": "met",
                "details": [],
                "max_points": 25
              },
              {
                "key": "documentation_homepage_site",
                "name": "Documentation / homepage site",
                "detail": "https://opendatalab.github.io/MinerU/",
                "points": 15,
                "status": "met",
                "details": [],
                "max_points": 15
              },
              {
                "key": "repository_description",
                "name": "Repository description",
                "detail": null,
                "points": 10,
                "status": "met",
                "details": [],
                "max_points": 10
              },
              {
                "key": "topics",
                "name": "Topics",
                "detail": "16 topics",
                "points": 10,
                "status": "met",
                "details": [
                  {
                    "code": "topics_count",
                    "params": {
                      "count": 16
                    }
                  }
                ],
                "max_points": 10
              },
              {
                "key": "wiki",
                "name": "Wiki",
                "detail": null,
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 10
              }
            ]
          }
        ],
        "description": "Are baseline engineering and documentation practices in place?"
      },
      {
        "key": "security",
        "band": "at_risk",
        "name": "Security",
        "value": 47,
        "weight": 0.16,
        "metrics": [
          {
            "key": "security_posture",
            "band": "at_risk",
            "name": "Security posture",
            "note": "Excluded from scoring (no data or not applicable): Packaging. Remaining weights renormalized.",
            "notes": [
              {
                "code": "excluded_no_data",
                "params": {
                  "components": [
                    "packaging"
                  ]
                }
              },
              {
                "code": "weights_renormalized",
                "params": {}
              }
            ],
            "value": 47,
            "inputs": {
              "source": "openssf_scorecard",
              "checks_evaluated": 17,
              "scorecard_version": "v5.5.0",
              "checks_inconclusive": 1,
              "scorecard_aggregate": 4.7
            },
            "components": [
              {
                "key": "binary_artifacts",
                "name": "Binary-Artifacts",
                "detail": "no binaries found in the repo",
                "points": 7.5,
                "status": "met",
                "details": [],
                "max_points": 7.5
              },
              {
                "key": "branch_protection",
                "name": "Branch-Protection",
                "detail": "branch protection is not maximal on development and all release branches",
                "points": 2.2,
                "status": "partial",
                "details": [],
                "max_points": 7.5
              },
              {
                "key": "ci_tests",
                "name": "CI-Tests",
                "detail": "16 out of 16 merged PRs checked by a CI test -- score normalized to 10",
                "points": 2.5,
                "status": "met",
                "details": [],
                "max_points": 2.5
              },
              {
                "key": "cii_best_practices",
                "name": "CII-Best-Practices",
                "detail": "no effort to earn an OpenSSF best practices badge detected",
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 2.5
              },
              {
                "key": "code_review",
                "name": "Code-Review",
                "detail": "Found 0/19 approved changesets -- score normalized to 0",
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 7.5
              },
              {
                "key": "contributors",
                "name": "Contributors",
                "detail": "project has 7 contributing companies or organizations",
                "points": 2.5,
                "status": "met",
                "details": [],
                "max_points": 2.5
              },
              {
                "key": "dangerous_workflow",
                "name": "Dangerous-Workflow",
                "detail": "no dangerous workflow patterns detected",
                "points": 10,
                "status": "met",
                "details": [],
                "max_points": 10
              },
              {
                "key": "dependency_update_tool",
                "name": "Dependency-Update-Tool",
                "detail": "no update tool detected",
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 7.5
              },
              {
                "key": "fuzzing",
                "name": "Fuzzing",
                "detail": "project is not fuzzed",
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 5
              },
              {
                "key": "license",
                "name": "License",
                "detail": "license file detected",
                "points": 2.2,
                "status": "partial",
                "details": [],
                "max_points": 2.5
              },
              {
                "key": "maintained",
                "name": "Maintained",
                "detail": "30 commit(s) and 16 issue activity found in the last 90 days -- score normalized to 10",
                "points": 7.5,
                "status": "met",
                "details": [],
                "max_points": 7.5
              },
              {
                "key": "packaging",
                "name": "Packaging",
                "detail": "packaging workflow not detected",
                "points": 0,
                "status": "excluded",
                "details": [
                  {
                    "code": "no_data",
                    "params": {}
                  }
                ],
                "max_points": 5
              },
              {
                "key": "pinned_dependencies",
                "name": "Pinned-Dependencies",
                "detail": "dependency not pinned by hash detected -- score normalized to 0",
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 5
              },
              {
                "key": "sast",
                "name": "SAST",
                "detail": "SAST tool is not run on all commits -- score normalized to 0",
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 5
              },
              {
                "key": "security_policy",
                "name": "Security-Policy",
                "detail": "security policy file detected",
                "points": 5,
                "status": "met",
                "details": [],
                "max_points": 5
              },
              {
                "key": "signed_releases",
                "name": "Signed-Releases",
                "detail": "Project has not signed or included provenance with any releases.",
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 7.5
              },
              {
                "key": "token_permissions",
                "name": "Token-Permissions",
                "detail": "detected GitHub workflow tokens with excessive permissions",
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 7.5
              },
              {
                "key": "vulnerabilities",
                "name": "Vulnerabilities",
                "detail": "0 existing vulnerabilities detected",
                "points": 7.5,
                "status": "met",
                "details": [],
                "max_points": 7.5
              }
            ]
          },
          {
            "key": "high_risk_jurisdiction_exposure",
            "band": "excellent",
            "name": "High-Risk Jurisdiction Exposure",
            "note": "Only high-confidence self-published location evidence affects this multiplier. Ambiguous matches are review-only; country evidence is not proof of nationality, citizenship, legal registration, malicious intent, or sanctions status.",
            "notes": [
              {
                "code": "jurisdiction_evidence_limits",
                "params": {}
              }
            ],
            "value": 100,
            "inputs": {
              "meaning": "self-published location evidence; not nationality or citizenship",
              "red_flag": false,
              "exposures": [],
              "policy_countries": [
                "Russia",
                "Iran",
                "North Korea"
              ],
              "review_only_matches": 0,
              "assessed_self_published_locations": 7
            },
            "components": [
              {
                "key": "policy_exposure_multiplier",
                "name": "Policy exposure multiplier",
                "detail": "no confirmed policy-scope location match",
                "points": 100,
                "status": "met",
                "details": [
                  {
                    "code": "jurisdiction_no_match",
                    "params": {}
                  }
                ],
                "max_points": 100
              }
            ]
          }
        ],
        "description": "Are visible security and supply-chain practices strong, with no malicious dependency and no unresolved high-risk jurisdiction exposure?"
      },
      {
        "key": "ai_readiness",
        "band": "critical",
        "name": "AI Readiness",
        "value": 28,
        "weight": 0,
        "metrics": [
          {
            "key": "ai_agent_context",
            "band": "critical",
            "name": "Agent context & guidance",
            "note": "Excluded from scoring (no data or not applicable): Legible commit history. Remaining weights renormalized.",
            "notes": [
              {
                "code": "excluded_no_data",
                "params": {
                  "components": [
                    "legible_commit_history"
                  ]
                }
              },
              {
                "code": "weights_renormalized",
                "params": {}
              }
            ],
            "value": 1,
            "inputs": {
              "has_llms_txt": false,
              "legible_history_share": null,
              "agent_instruction_files": [],
              "agent_instruction_max_bytes": null
            },
            "components": [
              {
                "key": "agent_instructions",
                "name": "Agent instructions",
                "detail": "no CLAUDE.md / AGENTS.md / editor rules",
                "points": 0,
                "status": "missed",
                "details": [
                  {
                    "code": "no_agent_instructions",
                    "params": {}
                  }
                ],
                "max_points": 45
              },
              {
                "key": "machine_readable_docs_llms_txt",
                "name": "Machine-readable docs (llms.txt)",
                "detail": null,
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 15
              },
              {
                "key": "legible_commit_history",
                "name": "Legible commit history",
                "detail": "no data",
                "points": 0,
                "status": "excluded",
                "details": [
                  {
                    "code": "no_data",
                    "params": {}
                  }
                ],
                "max_points": 40
              }
            ]
          },
          {
            "key": "ai_verify_loop",
            "band": "at_risk",
            "name": "Verify loop (build / test / typecheck)",
            "note": "Excluded from scoring (no data or not applicable): Demonstrated agent practice, Automated maintenance. Remaining weights renormalized.",
            "notes": [
              {
                "code": "excluded_no_data",
                "params": {
                  "components": [
                    "demonstrated_agent_practice",
                    "automated_maintenance"
                  ]
                }
              },
              {
                "code": "weights_renormalized",
                "params": {}
              }
            ],
            "value": 39,
            "inputs": {
              "has_nix": false,
              "has_tests": true,
              "lockfiles": [],
              "has_dockerfile": true,
              "typed_language": false,
              "bootstrap_files": [],
              "has_devcontainer": false,
              "has_linter_config": false,
              "typecheck_configs": [],
              "agent_commit_share": null,
              "toolchain_manifests": [],
              "dependency_bot_commit_share": null
            },
            "components": [
              {
                "key": "one_command_bootstrap",
                "name": "One-command bootstrap",
                "detail": null,
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 18
              },
              {
                "key": "automated_tests",
                "name": "Automated tests",
                "detail": null,
                "points": 22,
                "status": "met",
                "details": [],
                "max_points": 22
              },
              {
                "key": "lint_format_config",
                "name": "Lint / format config",
                "detail": null,
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 11
              },
              {
                "key": "static_type_checking",
                "name": "Static type checking",
                "detail": null,
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 11
              },
              {
                "key": "reproducible_environment",
                "name": "Reproducible environment",
                "detail": "Dockerfile",
                "points": 10,
                "status": "met",
                "details": [
                  {
                    "code": "file_list",
                    "params": {
                      "files": "Dockerfile"
                    }
                  }
                ],
                "max_points": 10
              },
              {
                "key": "demonstrated_agent_practice",
                "name": "Demonstrated agent practice",
                "detail": "no data",
                "points": 0,
                "status": "excluded",
                "details": [
                  {
                    "code": "no_data",
                    "params": {}
                  }
                ],
                "max_points": 10
              },
              {
                "key": "automated_maintenance",
                "name": "Automated maintenance",
                "detail": "no data",
                "points": 0,
                "status": "excluded",
                "details": [
                  {
                    "code": "no_data",
                    "params": {}
                  }
                ],
                "max_points": 8
              },
              {
                "key": "openssf_scorecard_pinned_dependencies",
                "name": "OpenSSF Scorecard: Pinned-Dependencies",
                "detail": "dependency not pinned by hash detected -- score normalized to 0",
                "points": 0,
                "status": "missed",
                "details": [],
                "max_points": 10
              }
            ]
          },
          {
            "key": "ai_code_legibility",
            "band": "moderate",
            "name": "Code legibility for models",
            "note": null,
            "notes": [],
            "value": 53,
            "inputs": {
              "primary_language": "Python",
              "largest_source_bytes": 140821,
              "source_files_sampled": 222,
              "oversized_source_files": 8
            },
            "components": [
              {
                "key": "type_checkable_code",
                "name": "Type-checkable code",
                "detail": "Python without a type-check config",
                "points": 0,
                "status": "missed",
                "details": [
                  {
                    "code": "no_typecheck_config_language",
                    "params": {
                      "language": "Python"
                    }
                  }
                ],
                "max_points": 45
              },
              {
                "key": "manageable_file_sizes",
                "name": "Manageable file sizes",
                "detail": "8/222 source files over 60KB",
                "points": 53,
                "status": "partial",
                "details": [
                  {
                    "code": "oversized_source_files",
                    "params": {
                      "kb": 60,
                      "sampled": 222,
                      "oversized": 8
                    }
                  }
                ],
                "max_points": 55
              }
            ]
          }
        ],
        "description": "How well is the repo equipped to be developed and maintained with AI coding agents? An independent, experimental badge — weight 0.0, so it is surfaced on its own and does not affect the overall health score."
      }
    ],
    "metrics_version": "1.13.0"
  },
  "warnings": [],
  "report_type": "repository",
  "generated_at": "2026-07-13T01:20:23.016320Z",
  "schema_version": "0.9.0",
  "badge_url": "https://raw.githubusercontent.com/inspect-software/badges/main/v1/o/opendatalab/MinerU.svg",
  "full_name": "opendatalab/MinerU",
  "license_state": "custom",
  "license_spdx": null
}