{
  "name": "Data Stack Index — data observability dataset",
  "description": "Independent, source-verified structured profiles of data observability, quality, catalog, and lineage tools. Hand-written from public documentation; no vendor-supplied content.",
  "homepage": "https://datastackindex.com",
  "license": "https://datastackindex.com/terms/",
  "generated": "2026-07-09",
  "count": 24,
  "fields_reference": "https://datastackindex.com/methodology/",
  "tools": [
    {
      "slug": "acceldata",
      "url": "https://datastackindex.com/data-observability/tools/acceldata/",
      "name": "Acceldata",
      "vendor": "Acceldata",
      "homepage": "https://www.acceldata.io",
      "repo": null,
      "docs_url": "https://docs.acceldata.io",
      "founded_year": 2018,
      "headquarters": "Campbell, CA",
      "status": "active",
      "primary_cluster": "quality_testing",
      "cluster_strength": {
        "quality_testing": 3,
        "catalog_discovery": 2,
        "lineage_metadata": 2
      },
      "deployment": "hybrid",
      "license_type": "proprietary",
      "license_spdx": null,
      "target_persona": [
        "data_engineer",
        "platform_engineer",
        "data_steward",
        "chief_data_officer",
        "governance_lead"
      ],
      "company_size_fit": [
        "mid_market",
        "enterprise"
      ],
      "warehouse_native_support": [
        "snowflake",
        "databricks",
        "bigquery",
        "redshift",
        "postgres",
        "mysql",
        "mssql",
        "athena",
        "synapse",
        "trino",
        "clickhouse"
      ],
      "dbt_integration": "native",
      "airflow_integration": "plugin",
      "openlineage_support": "none",
      "api_access": "full",
      "pricing_model": "capacity_based",
      "published_pricing": false,
      "pricing_starts_at_usd": null,
      "pricing_unit": "custom",
      "has_free_tier": false,
      "has_oss_self_host": false,
      "quality_testing": {
        "test_authoring": "code_first_plus_gui",
        "test_paradigm": "both",
        "ml_anomaly_detection": true,
        "ml_training_window": "Learns data patterns automatically; configurable sensitivity (low/medium/high) with a human-feedback retraining loop",
        "root_cause_analysis": true,
        "incident_management": true,
        "circuit_breaker_support": false,
        "freshness_monitoring": true,
        "volume_monitoring": true,
        "schema_change_detection": true,
        "column_level_profiling": true,
        "custom_sql_checks": true,
        "data_contracts_enforcement": false,
        "monitors_at": [
          "warehouse_table",
          "warehouse_column",
          "file_object",
          "pipeline_task",
          "dbt_model",
          "streaming_topic"
        ],
        "dbt_native": false,
        "dbt_test_compatible": true,
        "runs_in_ci": false,
        "runs_pre_merge": false,
        "alerting_channels": [
          "slack",
          "email"
        ]
      },
      "catalog_discovery": {
        "asset_types_supported": [
          "tables",
          "columns",
          "files",
          "pipelines"
        ],
        "metadata_ingestion": "pull_connectors",
        "connector_count": null,
        "search_approach": "hybrid",
        "natural_language_search": true,
        "business_glossary": true,
        "glossary_linking_to_assets": true,
        "ownership_tracking": true,
        "data_contracts": false,
        "governance_workflows": true,
        "access_request_workflow": false,
        "pii_auto_classification": true,
        "tag_propagation": true,
        "collaboration_features": [
          "slack_integration"
        ],
        "free_self_hosted_available": false,
        "managed_version_of_oss": null
      },
      "lineage_metadata": {
        "lineage_granularity": "both",
        "lineage_extraction_method": [
          "dbt_manifest",
          "query_log_parsing"
        ],
        "cross_system_lineage": true,
        "bi_tool_lineage": [
          "tableau",
          "power-bi",
          "looker"
        ],
        "upstream_source_lineage": true,
        "impact_analysis": true,
        "reverse_impact_analysis": false,
        "openlineage_conformance": "none",
        "historical_lineage": false,
        "lineage_api": true,
        "lineage_diff": false
      },
      "key_features": [
        "ml-anomaly-detection",
        "assertion-based-testing",
        "warehouse-native-monitoring",
        "schema-change-detection",
        "column-level-lineage",
        "business-glossary",
        "pii-auto-classification"
      ],
      "notable_missing": [
        "openlineage-native",
        "pre-merge-diffing",
        "dbt-native-testing",
        "data-contracts"
      ],
      "common_alternatives": [
        "monte-carlo",
        "bigeye",
        "anomalo"
      ],
      "one_liner": "Enterprise data observability with ML data quality, reconciliation, and a built-in catalog — strong on hybrid and on-prem estates.",
      "last_verified": "2026-05-30"
    },
    {
      "slug": "alation",
      "url": "https://datastackindex.com/data-observability/tools/alation/",
      "name": "Alation",
      "vendor": "Alation",
      "homepage": "https://www.alation.com",
      "repo": null,
      "docs_url": "https://www.alation.com/docs/en/latest/",
      "founded_year": 2012,
      "headquarters": "Redwood City, CA",
      "status": "active",
      "primary_cluster": "catalog_discovery",
      "cluster_strength": {
        "quality_testing": 0,
        "catalog_discovery": 3,
        "lineage_metadata": 3
      },
      "deployment": "both",
      "license_type": "proprietary",
      "license_spdx": null,
      "target_persona": [
        "data_steward",
        "governance_lead",
        "chief_data_officer",
        "analyst",
        "data_engineer"
      ],
      "company_size_fit": [
        "mid_market",
        "enterprise"
      ],
      "warehouse_native_support": [
        "snowflake",
        "bigquery",
        "redshift",
        "databricks",
        "postgres",
        "mysql",
        "mssql",
        "athena",
        "synapse"
      ],
      "dbt_integration": "metadata_sync",
      "airflow_integration": "metadata_sync",
      "openlineage_support": "consumer",
      "api_access": "full",
      "pricing_model": "per_seat_tiered",
      "published_pricing": false,
      "pricing_starts_at_usd": null,
      "pricing_unit": "per_seat",
      "has_free_tier": false,
      "has_oss_self_host": false,
      "quality_testing": null,
      "catalog_discovery": {
        "asset_types_supported": [
          "tables",
          "columns",
          "dashboards",
          "reports",
          "files",
          "topics",
          "glossary_terms"
        ],
        "metadata_ingestion": "both",
        "connector_count": 120,
        "search_approach": "hybrid",
        "natural_language_search": true,
        "business_glossary": true,
        "glossary_linking_to_assets": true,
        "ownership_tracking": true,
        "data_contracts": false,
        "governance_workflows": true,
        "access_request_workflow": true,
        "pii_auto_classification": true,
        "tag_propagation": true,
        "collaboration_features": [
          "comments",
          "q_and_a",
          "slack_integration"
        ],
        "free_self_hosted_available": false,
        "managed_version_of_oss": null
      },
      "lineage_metadata": {
        "lineage_granularity": "column_level",
        "lineage_extraction_method": [
          "sql_static_analysis",
          "query_log_parsing",
          "openlineage_events",
          "api_push"
        ],
        "cross_system_lineage": true,
        "bi_tool_lineage": [
          "tableau",
          "power-bi",
          "looker"
        ],
        "upstream_source_lineage": true,
        "impact_analysis": true,
        "reverse_impact_analysis": true,
        "openlineage_conformance": "consumer",
        "historical_lineage": true,
        "lineage_api": true,
        "lineage_diff": false
      },
      "key_features": [
        "business-glossary",
        "column-level-lineage",
        "table-level-lineage",
        "pii-auto-classification",
        "transformation-lineage",
        "reverse-impact-analysis"
      ],
      "notable_missing": [
        "pre-merge-diffing",
        "dbt-native-testing",
        "ml-anomaly-detection",
        "data-contracts"
      ],
      "common_alternatives": [
        "atlan",
        "collibra",
        "secoda",
        "datahub",
        "openmetadata",
        "select-star"
      ],
      "one_liner": "The incumbent that defined the data catalog — behavioral search, deep governance, and strong column-level lineage.",
      "last_verified": "2026-07-03"
    },
    {
      "slug": "amundsen",
      "url": "https://datastackindex.com/data-observability/tools/amundsen/",
      "name": "Amundsen",
      "vendor": "LF AI & Data Foundation",
      "homepage": "https://www.amundsen.io",
      "repo": "https://github.com/amundsen-io/amundsen",
      "docs_url": "https://www.amundsen.io/amundsen/",
      "founded_year": 2019,
      "headquarters": null,
      "status": "active",
      "primary_cluster": "catalog_discovery",
      "cluster_strength": {
        "quality_testing": 0,
        "catalog_discovery": 3,
        "lineage_metadata": 1
      },
      "deployment": "self_hosted",
      "license_type": "open_source",
      "license_spdx": "Apache-2.0",
      "target_persona": [
        "data_engineer",
        "platform_engineer",
        "analyst"
      ],
      "company_size_fit": [
        "scaleup",
        "mid_market"
      ],
      "warehouse_native_support": [
        "snowflake",
        "bigquery",
        "redshift",
        "databricks",
        "postgres",
        "mysql",
        "mssql",
        "trino",
        "athena"
      ],
      "dbt_integration": "plugin",
      "airflow_integration": "plugin",
      "openlineage_support": "consumer",
      "api_access": "full",
      "pricing_model": "free_forever",
      "published_pricing": true,
      "pricing_starts_at_usd": 0,
      "pricing_unit": "custom",
      "has_free_tier": true,
      "has_oss_self_host": true,
      "quality_testing": null,
      "catalog_discovery": {
        "asset_types_supported": [
          "tables",
          "columns",
          "dashboards",
          "ml_features"
        ],
        "metadata_ingestion": "pull_connectors",
        "connector_count": null,
        "search_approach": "keyword",
        "natural_language_search": false,
        "business_glossary": false,
        "glossary_linking_to_assets": false,
        "ownership_tracking": true,
        "data_contracts": false,
        "governance_workflows": false,
        "access_request_workflow": false,
        "pii_auto_classification": false,
        "tag_propagation": false,
        "collaboration_features": [],
        "free_self_hosted_available": true,
        "managed_version_of_oss": null
      },
      "lineage_metadata": {
        "lineage_granularity": "table_level",
        "lineage_extraction_method": [
          "openlineage_events",
          "api_push"
        ],
        "cross_system_lineage": false,
        "bi_tool_lineage": [
          "tableau",
          "mode",
          "redash"
        ],
        "upstream_source_lineage": false,
        "impact_analysis": false,
        "reverse_impact_analysis": false,
        "openlineage_conformance": "consumer",
        "historical_lineage": false,
        "lineage_api": true,
        "lineage_diff": false
      },
      "key_features": [
        "table-level-lineage"
      ],
      "notable_missing": [
        "business-glossary",
        "column-level-lineage",
        "pii-auto-classification",
        "data-contracts"
      ],
      "common_alternatives": [
        "datahub",
        "openmetadata",
        "apache-atlas",
        "select-star"
      ],
      "one_liner": "The Lyft-born OSS catalog that invented search-first discovery — historically important, but development has largely stalled since 2024.",
      "last_verified": "2026-07-03"
    },
    {
      "slug": "anomalo",
      "url": "https://datastackindex.com/data-observability/tools/anomalo/",
      "name": "Anomalo",
      "vendor": "Anomalo",
      "homepage": "https://www.anomalo.com",
      "repo": null,
      "docs_url": "https://docs.anomalo.com",
      "founded_year": 2018,
      "headquarters": null,
      "status": "active",
      "primary_cluster": "quality_testing",
      "cluster_strength": {
        "quality_testing": 3,
        "catalog_discovery": 0,
        "lineage_metadata": 0
      },
      "deployment": "both",
      "license_type": "proprietary",
      "license_spdx": null,
      "target_persona": [
        "data_engineer",
        "analytics_engineer",
        "data_steward",
        "governance_lead",
        "chief_data_officer"
      ],
      "company_size_fit": [
        "mid_market",
        "enterprise"
      ],
      "warehouse_native_support": [
        "snowflake",
        "bigquery",
        "redshift",
        "databricks",
        "postgres",
        "mysql",
        "mssql",
        "athena",
        "trino"
      ],
      "dbt_integration": "metadata_sync",
      "airflow_integration": "native",
      "openlineage_support": "none",
      "api_access": "full",
      "pricing_model": "enterprise_only",
      "published_pricing": false,
      "pricing_starts_at_usd": null,
      "pricing_unit": "custom",
      "has_free_tier": false,
      "has_oss_self_host": false,
      "quality_testing": {
        "test_authoring": "gui",
        "test_paradigm": "both",
        "ml_anomaly_detection": true,
        "ml_training_window": null,
        "root_cause_analysis": true,
        "incident_management": true,
        "circuit_breaker_support": true,
        "freshness_monitoring": true,
        "volume_monitoring": true,
        "schema_change_detection": true,
        "column_level_profiling": true,
        "custom_sql_checks": true,
        "data_contracts_enforcement": false,
        "monitors_at": [
          "warehouse_table",
          "warehouse_column",
          "dbt_model",
          "file_object"
        ],
        "dbt_native": false,
        "dbt_test_compatible": true,
        "runs_in_ci": true,
        "runs_pre_merge": false,
        "alerting_channels": [
          "slack",
          "teams",
          "email",
          "webhook",
          "pagerduty",
          "opsgenie",
          "jira"
        ]
      },
      "catalog_discovery": null,
      "lineage_metadata": null,
      "key_features": [
        "ml-anomaly-detection",
        "schema-change-detection",
        "warehouse-native-monitoring",
        "pii-auto-classification"
      ],
      "notable_missing": [
        "dbt-native-testing",
        "openlineage-native",
        "pre-merge-diffing",
        "data-contracts"
      ],
      "common_alternatives": [
        "monte-carlo",
        "bigeye",
        "soda"
      ],
      "one_liner": "GUI-first ML anomaly detection at petabyte scale — pivoting in 2026 around agentic AI and unstructured-data monitoring.",
      "last_verified": "2026-05-08"
    },
    {
      "slug": "apache-atlas",
      "url": "https://datastackindex.com/data-observability/tools/apache-atlas/",
      "name": "Apache Atlas",
      "vendor": "Apache Software Foundation",
      "homepage": "https://atlas.apache.org",
      "repo": "https://github.com/apache/atlas",
      "docs_url": "https://atlas.apache.org",
      "founded_year": 2015,
      "headquarters": null,
      "status": "active",
      "primary_cluster": "catalog_discovery",
      "cluster_strength": {
        "quality_testing": 0,
        "catalog_discovery": 3,
        "lineage_metadata": 2
      },
      "deployment": "self_hosted",
      "license_type": "open_source",
      "license_spdx": "Apache-2.0",
      "target_persona": [
        "data_engineer",
        "platform_engineer",
        "governance_lead",
        "data_steward"
      ],
      "company_size_fit": [
        "mid_market",
        "enterprise"
      ],
      "warehouse_native_support": [
        "trino"
      ],
      "dbt_integration": "none",
      "airflow_integration": "none",
      "openlineage_support": "none",
      "api_access": "full",
      "pricing_model": "free_forever",
      "published_pricing": true,
      "pricing_starts_at_usd": 0,
      "pricing_unit": "custom",
      "has_free_tier": true,
      "has_oss_self_host": true,
      "quality_testing": null,
      "catalog_discovery": {
        "asset_types_supported": [
          "tables",
          "columns",
          "pipelines",
          "topics",
          "files",
          "glossary_terms"
        ],
        "metadata_ingestion": "both",
        "connector_count": 9,
        "search_approach": "keyword",
        "natural_language_search": false,
        "business_glossary": true,
        "glossary_linking_to_assets": true,
        "ownership_tracking": true,
        "data_contracts": false,
        "governance_workflows": false,
        "access_request_workflow": false,
        "pii_auto_classification": false,
        "tag_propagation": true,
        "collaboration_features": [],
        "free_self_hosted_available": true,
        "managed_version_of_oss": null
      },
      "lineage_metadata": {
        "lineage_granularity": "both",
        "lineage_extraction_method": [
          "plugin_instrumentation",
          "api_push"
        ],
        "cross_system_lineage": true,
        "bi_tool_lineage": [],
        "upstream_source_lineage": true,
        "impact_analysis": true,
        "reverse_impact_analysis": false,
        "openlineage_conformance": "none",
        "historical_lineage": false,
        "lineage_api": true,
        "lineage_diff": false
      },
      "key_features": [
        "column-level-lineage",
        "table-level-lineage",
        "business-glossary"
      ],
      "notable_missing": [
        "openlineage-native",
        "pii-auto-classification",
        "warehouse-native-monitoring",
        "reverse-impact-analysis"
      ],
      "common_alternatives": [
        "datahub",
        "openmetadata",
        "amundsen"
      ],
      "one_liner": "The ASF's Hadoop-native metadata framework — typed entities, classification propagation via lineage, and Ranger-enforced policies.",
      "last_verified": "2026-07-03"
    },
    {
      "slug": "atlan",
      "url": "https://datastackindex.com/data-observability/tools/atlan/",
      "name": "Atlan",
      "vendor": "Atlan",
      "homepage": "https://atlan.com",
      "repo": null,
      "docs_url": "https://docs.atlan.com",
      "founded_year": 2019,
      "headquarters": "Singapore",
      "status": "active",
      "primary_cluster": "catalog_discovery",
      "cluster_strength": {
        "quality_testing": 0,
        "catalog_discovery": 3,
        "lineage_metadata": 3
      },
      "deployment": "hybrid",
      "license_type": "proprietary",
      "license_spdx": null,
      "target_persona": [
        "data_steward",
        "governance_lead",
        "chief_data_officer",
        "analytics_engineer",
        "data_engineer"
      ],
      "company_size_fit": [
        "mid_market",
        "enterprise"
      ],
      "warehouse_native_support": [
        "snowflake",
        "bigquery",
        "databricks",
        "redshift",
        "postgres",
        "mysql",
        "mssql",
        "synapse",
        "fabric",
        "athena",
        "trino"
      ],
      "dbt_integration": "native",
      "airflow_integration": "native",
      "openlineage_support": "consumer",
      "api_access": "full",
      "pricing_model": "per_seat_tiered",
      "published_pricing": false,
      "pricing_starts_at_usd": null,
      "pricing_unit": "per_seat",
      "has_free_tier": false,
      "has_oss_self_host": false,
      "quality_testing": null,
      "catalog_discovery": {
        "asset_types_supported": [
          "tables",
          "columns",
          "dashboards",
          "reports",
          "dbt_models",
          "dbt_metrics",
          "dbt_sources",
          "ml_features",
          "ml_models",
          "notebooks",
          "pipelines",
          "topics",
          "files",
          "glossary_terms"
        ],
        "metadata_ingestion": "both",
        "connector_count": 80,
        "search_approach": "hybrid",
        "natural_language_search": true,
        "business_glossary": true,
        "glossary_linking_to_assets": true,
        "ownership_tracking": true,
        "data_contracts": true,
        "governance_workflows": true,
        "access_request_workflow": true,
        "pii_auto_classification": true,
        "tag_propagation": true,
        "collaboration_features": [
          "comments",
          "q_and_a",
          "slack_integration"
        ],
        "free_self_hosted_available": false,
        "managed_version_of_oss": null
      },
      "lineage_metadata": {
        "lineage_granularity": "column_level",
        "lineage_extraction_method": [
          "sql_static_analysis",
          "query_log_parsing",
          "openlineage_events",
          "dbt_manifest",
          "api_push"
        ],
        "cross_system_lineage": true,
        "bi_tool_lineage": [
          "looker",
          "tableau",
          "powerbi",
          "mode",
          "sigma",
          "thoughtspot"
        ],
        "upstream_source_lineage": true,
        "impact_analysis": true,
        "reverse_impact_analysis": true,
        "openlineage_conformance": "consumer",
        "historical_lineage": true,
        "lineage_api": true,
        "lineage_diff": false
      },
      "key_features": [
        "column-level-lineage",
        "business-glossary",
        "data-contracts",
        "pii-auto-classification",
        "openlineage-native"
      ],
      "notable_missing": [
        "pre-merge-diffing",
        "ml-anomaly-detection",
        "warehouse-native-monitoring"
      ],
      "common_alternatives": [
        "datahub",
        "openmetadata",
        "select-star"
      ],
      "one_liner": "Enterprise catalog and governance plane positioned as the AI context layer — connectors, lineage, contracts, and an MCP server for agents.",
      "last_verified": "2026-05-08"
    },
    {
      "slug": "bigeye",
      "url": "https://datastackindex.com/data-observability/tools/bigeye/",
      "name": "Bigeye",
      "vendor": "Bigeye",
      "homepage": "https://www.bigeye.com",
      "repo": null,
      "docs_url": "https://docs.bigeye.com",
      "founded_year": 2019,
      "headquarters": null,
      "status": "active",
      "primary_cluster": "quality_testing",
      "cluster_strength": {
        "quality_testing": 3,
        "catalog_discovery": 0,
        "lineage_metadata": 2
      },
      "deployment": "both",
      "license_type": "proprietary",
      "license_spdx": null,
      "target_persona": [
        "data_engineer",
        "analytics_engineer",
        "data_steward",
        "governance_lead",
        "chief_data_officer"
      ],
      "company_size_fit": [
        "mid_market",
        "enterprise"
      ],
      "warehouse_native_support": [
        "snowflake",
        "bigquery",
        "redshift",
        "databricks",
        "postgres",
        "mssql",
        "synapse"
      ],
      "dbt_integration": "metadata_sync",
      "airflow_integration": "plugin",
      "openlineage_support": "none",
      "api_access": "full",
      "pricing_model": "enterprise_only",
      "published_pricing": false,
      "pricing_starts_at_usd": null,
      "pricing_unit": "custom",
      "has_free_tier": false,
      "has_oss_self_host": false,
      "quality_testing": {
        "test_authoring": "code_first_plus_gui",
        "test_paradigm": "both",
        "ml_anomaly_detection": true,
        "ml_training_window": null,
        "root_cause_analysis": true,
        "incident_management": true,
        "circuit_breaker_support": true,
        "freshness_monitoring": true,
        "volume_monitoring": true,
        "schema_change_detection": true,
        "column_level_profiling": true,
        "custom_sql_checks": true,
        "data_contracts_enforcement": false,
        "monitors_at": [
          "warehouse_table",
          "warehouse_column",
          "dbt_model",
          "bi_dashboard"
        ],
        "dbt_native": false,
        "dbt_test_compatible": true,
        "runs_in_ci": true,
        "runs_pre_merge": false,
        "alerting_channels": [
          "slack",
          "email",
          "webhook",
          "pagerduty",
          "jira"
        ]
      },
      "catalog_discovery": null,
      "lineage_metadata": {
        "lineage_granularity": "column_level",
        "lineage_extraction_method": [
          "query_log_parsing",
          "dbt_manifest"
        ],
        "cross_system_lineage": true,
        "bi_tool_lineage": [
          "tableau",
          "looker",
          "power_bi"
        ],
        "upstream_source_lineage": false,
        "impact_analysis": true,
        "reverse_impact_analysis": true,
        "openlineage_conformance": "none",
        "historical_lineage": false,
        "lineage_api": true,
        "lineage_diff": false
      },
      "key_features": [
        "ml-anomaly-detection",
        "column-level-lineage",
        "schema-change-detection",
        "pii-auto-classification",
        "table-level-lineage"
      ],
      "notable_missing": [
        "dbt-native-testing",
        "openlineage-native",
        "pre-merge-diffing",
        "data-contracts"
      ],
      "common_alternatives": [
        "monte-carlo",
        "anomalo",
        "soda"
      ],
      "one_liner": "Enterprise data observability with Autometrics ML thresholds — repositioning in 2026 as an AI Trust Platform with runtime governance.",
      "last_verified": "2026-05-08"
    },
    {
      "slug": "cloudera-octopai",
      "url": "https://datastackindex.com/data-observability/tools/cloudera-octopai/",
      "name": "Cloudera Data Lineage (Octopai)",
      "vendor": "Cloudera",
      "homepage": "https://www.cloudera.com/products/unified-data-fabric/data-lineage.html",
      "repo": null,
      "docs_url": "https://docs.cloudera.com/octopai/latest/index.html",
      "founded_year": 2016,
      "headquarters": "Santa Clara, CA",
      "status": "acquired",
      "primary_cluster": "lineage_metadata",
      "cluster_strength": {
        "quality_testing": 0,
        "catalog_discovery": 2,
        "lineage_metadata": 3
      },
      "deployment": "saas",
      "license_type": "proprietary",
      "license_spdx": null,
      "target_persona": [
        "data_steward",
        "governance_lead",
        "data_engineer",
        "chief_data_officer"
      ],
      "company_size_fit": [
        "mid_market",
        "enterprise"
      ],
      "warehouse_native_support": [
        "snowflake",
        "redshift",
        "bigquery",
        "databricks",
        "postgres",
        "mssql",
        "synapse"
      ],
      "dbt_integration": "none",
      "airflow_integration": "metadata_sync",
      "openlineage_support": "none",
      "api_access": "full",
      "pricing_model": "capacity_based",
      "published_pricing": false,
      "pricing_starts_at_usd": null,
      "pricing_unit": "custom",
      "has_free_tier": false,
      "has_oss_self_host": false,
      "quality_testing": null,
      "catalog_discovery": {
        "asset_types_supported": [
          "tables",
          "columns",
          "dashboards",
          "reports",
          "pipelines",
          "glossary_terms"
        ],
        "metadata_ingestion": "crawlers",
        "connector_count": 60,
        "search_approach": "keyword",
        "natural_language_search": false,
        "business_glossary": true,
        "glossary_linking_to_assets": true,
        "ownership_tracking": true,
        "data_contracts": false,
        "governance_workflows": false,
        "access_request_workflow": false,
        "pii_auto_classification": true,
        "tag_propagation": true,
        "collaboration_features": [
          "comments"
        ],
        "free_self_hosted_available": false,
        "managed_version_of_oss": null
      },
      "lineage_metadata": {
        "lineage_granularity": "both",
        "lineage_extraction_method": [
          "sql_static_analysis",
          "query_log_parsing",
          "plugin_instrumentation"
        ],
        "cross_system_lineage": true,
        "bi_tool_lineage": [
          "tableau",
          "powerbi",
          "cognos",
          "microstrategy",
          "qlik",
          "sap-bo",
          "looker"
        ],
        "upstream_source_lineage": true,
        "impact_analysis": true,
        "reverse_impact_analysis": true,
        "openlineage_conformance": "none",
        "historical_lineage": true,
        "lineage_api": true,
        "lineage_diff": false
      },
      "key_features": [
        "column-level-lineage",
        "table-level-lineage",
        "transformation-lineage",
        "reverse-impact-analysis",
        "pii-auto-classification"
      ],
      "notable_missing": [
        "openlineage-native",
        "pre-merge-diffing",
        "data-contracts"
      ],
      "common_alternatives": [
        "atlan",
        "datahub"
      ],
      "one_liner": "SaaS lineage with 60+ connectors and a 24-hour deploy story — built for hybrid enterprise estates without IBM-stack baggage.",
      "last_verified": "2026-05-08"
    },
    {
      "slug": "collibra",
      "url": "https://datastackindex.com/data-observability/tools/collibra/",
      "name": "Collibra",
      "vendor": "Collibra",
      "homepage": "https://www.collibra.com",
      "repo": null,
      "docs_url": "https://productresources.collibra.com/docs/collibra/latest/",
      "founded_year": 2008,
      "headquarters": "Brussels, Belgium",
      "status": "active",
      "primary_cluster": "catalog_discovery",
      "cluster_strength": {
        "quality_testing": 2,
        "catalog_discovery": 3,
        "lineage_metadata": 3
      },
      "deployment": "saas",
      "license_type": "proprietary",
      "license_spdx": null,
      "target_persona": [
        "data_steward",
        "governance_lead",
        "chief_data_officer",
        "data_engineer"
      ],
      "company_size_fit": [
        "mid_market",
        "enterprise"
      ],
      "warehouse_native_support": [
        "snowflake",
        "databricks",
        "bigquery",
        "redshift",
        "synapse",
        "fabric",
        "postgres",
        "mssql"
      ],
      "dbt_integration": "plugin",
      "airflow_integration": "plugin",
      "openlineage_support": "consumer",
      "api_access": "full",
      "pricing_model": "per_seat_tiered",
      "published_pricing": false,
      "pricing_starts_at_usd": null,
      "pricing_unit": "per_seat",
      "has_free_tier": false,
      "has_oss_self_host": false,
      "quality_testing": {
        "test_authoring": "sql",
        "test_paradigm": "both",
        "ml_anomaly_detection": true,
        "ml_training_window": "Adaptive rules plus ML for outliers, drift, and silent schema changes (OwlDQ heritage); thresholds self-adjust over history",
        "root_cause_analysis": true,
        "incident_management": true,
        "circuit_breaker_support": false,
        "freshness_monitoring": true,
        "volume_monitoring": true,
        "schema_change_detection": true,
        "column_level_profiling": true,
        "custom_sql_checks": true,
        "data_contracts_enforcement": true,
        "monitors_at": [
          "warehouse_table",
          "warehouse_column"
        ],
        "dbt_native": false,
        "dbt_test_compatible": false,
        "runs_in_ci": false,
        "runs_pre_merge": false,
        "alerting_channels": [
          "email"
        ]
      },
      "catalog_discovery": {
        "asset_types_supported": [
          "tables",
          "columns",
          "dashboards",
          "reports",
          "glossary_terms"
        ],
        "metadata_ingestion": "both",
        "connector_count": 100,
        "search_approach": "keyword",
        "natural_language_search": true,
        "business_glossary": true,
        "glossary_linking_to_assets": true,
        "ownership_tracking": true,
        "data_contracts": true,
        "governance_workflows": true,
        "access_request_workflow": true,
        "pii_auto_classification": true,
        "tag_propagation": true,
        "collaboration_features": [
          "comments",
          "wiki"
        ],
        "free_self_hosted_available": false,
        "managed_version_of_oss": null
      },
      "lineage_metadata": {
        "lineage_granularity": "both",
        "lineage_extraction_method": [
          "sql_static_analysis",
          "openlineage_events",
          "api_push"
        ],
        "cross_system_lineage": true,
        "bi_tool_lineage": [
          "tableau",
          "power-bi",
          "looker"
        ],
        "upstream_source_lineage": true,
        "impact_analysis": true,
        "reverse_impact_analysis": true,
        "openlineage_conformance": "consumer",
        "historical_lineage": true,
        "lineage_api": true,
        "lineage_diff": false
      },
      "key_features": [
        "business-glossary",
        "data-contracts",
        "column-level-lineage",
        "pii-auto-classification",
        "ml-anomaly-detection",
        "reverse-impact-analysis",
        "transformation-lineage"
      ],
      "notable_missing": [
        "circuit-breaker",
        "pre-merge-diffing",
        "dbt-native-testing",
        "openlineage-native"
      ],
      "common_alternatives": [
        "atlan",
        "alation",
        "datahub",
        "openmetadata"
      ],
      "one_liner": "Enterprise data-and-AI governance incumbent: catalog, glossary, workflow stewardship, lineage, and a separate ML data-quality module.",
      "last_verified": "2026-07-03"
    },
    {
      "slug": "datafold",
      "url": "https://datastackindex.com/data-observability/tools/datafold/",
      "name": "Datafold",
      "vendor": "Datafold",
      "homepage": "https://www.datafold.com",
      "repo": null,
      "docs_url": "https://docs.datafold.com",
      "founded_year": 2020,
      "headquarters": "San Francisco, CA",
      "status": "active",
      "primary_cluster": "quality_testing",
      "cluster_strength": {
        "quality_testing": 3,
        "catalog_discovery": 0,
        "lineage_metadata": 3
      },
      "deployment": "both",
      "license_type": "proprietary",
      "license_spdx": null,
      "target_persona": [
        "analytics_engineer",
        "data_engineer",
        "platform_engineer"
      ],
      "company_size_fit": [
        "scaleup",
        "mid_market",
        "enterprise"
      ],
      "warehouse_native_support": [
        "bigquery",
        "snowflake",
        "redshift",
        "databricks",
        "postgres",
        "mysql",
        "mssql",
        "clickhouse",
        "duckdb"
      ],
      "dbt_integration": "native",
      "airflow_integration": "native",
      "openlineage_support": "none",
      "api_access": "full",
      "pricing_model": "per_seat_tiered",
      "published_pricing": true,
      "pricing_starts_at_usd": 799,
      "pricing_unit": "custom",
      "has_free_tier": true,
      "has_oss_self_host": false,
      "quality_testing": {
        "test_authoring": "code_first_plus_gui",
        "test_paradigm": "assertion_based",
        "ml_anomaly_detection": false,
        "ml_training_window": null,
        "root_cause_analysis": true,
        "incident_management": false,
        "circuit_breaker_support": true,
        "freshness_monitoring": true,
        "volume_monitoring": true,
        "schema_change_detection": true,
        "column_level_profiling": true,
        "custom_sql_checks": true,
        "data_contracts_enforcement": false,
        "monitors_at": [
          "warehouse_table",
          "warehouse_column",
          "dbt_model"
        ],
        "dbt_native": true,
        "dbt_test_compatible": true,
        "runs_in_ci": true,
        "runs_pre_merge": true,
        "alerting_channels": [
          "slack",
          "email",
          "webhook"
        ]
      },
      "catalog_discovery": null,
      "lineage_metadata": {
        "lineage_granularity": "column_level",
        "lineage_extraction_method": [
          "sql_static_analysis",
          "dbt_manifest"
        ],
        "cross_system_lineage": true,
        "bi_tool_lineage": [
          "looker",
          "tableau",
          "mode"
        ],
        "upstream_source_lineage": false,
        "impact_analysis": true,
        "reverse_impact_analysis": true,
        "openlineage_conformance": "none",
        "historical_lineage": false,
        "lineage_api": true,
        "lineage_diff": true
      },
      "key_features": [
        "pre-merge-diffing",
        "column-level-lineage",
        "assertion-based-testing",
        "schema-change-detection",
        "dbt-native-testing"
      ],
      "notable_missing": [
        "ml-anomaly-detection",
        "openlineage-native",
        "business-glossary"
      ],
      "common_alternatives": [
        "elementary",
        "monte-carlo"
      ],
      "one_liner": "Pre-merge data diffing and column-level lineage — the tool that shifts data quality left into the pull request.",
      "last_verified": "2026-04-25"
    },
    {
      "slug": "datahub",
      "url": "https://datastackindex.com/data-observability/tools/datahub/",
      "name": "DataHub",
      "vendor": "Acryl Data",
      "homepage": "https://datahub.com",
      "repo": "https://github.com/datahub-project/datahub",
      "docs_url": "https://docs.datahub.com",
      "founded_year": 2021,
      "headquarters": "Palo Alto, CA",
      "status": "active",
      "primary_cluster": "catalog_discovery",
      "cluster_strength": {
        "quality_testing": 2,
        "catalog_discovery": 3,
        "lineage_metadata": 3
      },
      "deployment": "both",
      "license_type": "open_source",
      "license_spdx": "Apache-2.0",
      "target_persona": [
        "data_engineer",
        "platform_engineer",
        "data_steward",
        "analytics_engineer",
        "governance_lead"
      ],
      "company_size_fit": [
        "scaleup",
        "mid_market",
        "enterprise"
      ],
      "warehouse_native_support": [
        "snowflake",
        "bigquery",
        "redshift",
        "databricks",
        "postgres",
        "mysql",
        "mssql",
        "clickhouse",
        "trino",
        "athena",
        "synapse",
        "fabric"
      ],
      "dbt_integration": "native",
      "airflow_integration": "native",
      "openlineage_support": "consumer",
      "api_access": "full",
      "pricing_model": "open_core",
      "published_pricing": false,
      "pricing_starts_at_usd": null,
      "pricing_unit": "custom",
      "has_free_tier": true,
      "has_oss_self_host": true,
      "quality_testing": {
        "test_authoring": "yaml",
        "test_paradigm": "assertion_based",
        "ml_anomaly_detection": true,
        "ml_training_window": null,
        "root_cause_analysis": true,
        "incident_management": true,
        "circuit_breaker_support": false,
        "freshness_monitoring": true,
        "volume_monitoring": true,
        "schema_change_detection": true,
        "column_level_profiling": true,
        "custom_sql_checks": true,
        "data_contracts_enforcement": true,
        "monitors_at": [
          "warehouse_table",
          "warehouse_column",
          "dbt_model"
        ],
        "dbt_native": true,
        "dbt_test_compatible": true,
        "runs_in_ci": false,
        "runs_pre_merge": false,
        "alerting_channels": [
          "slack",
          "email",
          "webhook",
          "pagerduty"
        ]
      },
      "catalog_discovery": {
        "asset_types_supported": [
          "tables",
          "columns",
          "dashboards",
          "reports",
          "dbt_models",
          "dbt_metrics",
          "dbt_sources",
          "ml_features",
          "ml_models",
          "notebooks",
          "pipelines",
          "topics",
          "files",
          "glossary_terms"
        ],
        "metadata_ingestion": "both",
        "connector_count": 80,
        "search_approach": "hybrid",
        "natural_language_search": true,
        "business_glossary": true,
        "glossary_linking_to_assets": true,
        "ownership_tracking": true,
        "data_contracts": true,
        "governance_workflows": true,
        "access_request_workflow": true,
        "pii_auto_classification": true,
        "tag_propagation": true,
        "collaboration_features": [
          "comments",
          "q_and_a",
          "slack_integration"
        ],
        "free_self_hosted_available": true,
        "managed_version_of_oss": null
      },
      "lineage_metadata": {
        "lineage_granularity": "column_level",
        "lineage_extraction_method": [
          "sql_static_analysis",
          "query_log_parsing",
          "dbt_manifest",
          "openlineage_events",
          "plugin_instrumentation",
          "api_push"
        ],
        "cross_system_lineage": true,
        "bi_tool_lineage": [
          "tableau",
          "looker",
          "powerbi",
          "superset",
          "mode",
          "metabase",
          "redash"
        ],
        "upstream_source_lineage": true,
        "impact_analysis": true,
        "reverse_impact_analysis": true,
        "openlineage_conformance": "consumer",
        "historical_lineage": true,
        "lineage_api": true,
        "lineage_diff": false
      },
      "key_features": [
        "column-level-lineage",
        "business-glossary",
        "openlineage-native",
        "data-contracts",
        "schema-change-detection",
        "table-level-lineage"
      ],
      "notable_missing": [
        "pre-merge-diffing",
        "warehouse-native-monitoring"
      ],
      "common_alternatives": [
        "openmetadata",
        "atlan",
        "amundsen",
        "apache-atlas"
      ],
      "one_liner": "Apache-2.0 metadata platform with a serious managed counterpart — strongest event-driven architecture and column-level SQL lineage in OSS.",
      "last_verified": "2026-05-08"
    },
    {
      "slug": "dbt-expectations",
      "url": "https://datastackindex.com/data-observability/tools/dbt-expectations/",
      "name": "dbt-expectations",
      "vendor": "Metaplane (Datadog)",
      "homepage": "https://hub.getdbt.com/metaplane/dbt_expectations/latest/",
      "repo": "https://github.com/metaplane/dbt-expectations",
      "docs_url": "https://hub.getdbt.com/metaplane/dbt_expectations/latest/",
      "founded_year": 2020,
      "headquarters": null,
      "status": "active",
      "primary_cluster": "quality_testing",
      "cluster_strength": {
        "quality_testing": 3,
        "catalog_discovery": 0,
        "lineage_metadata": 0
      },
      "deployment": "self_hosted",
      "license_type": "open_source",
      "license_spdx": "Apache-2.0",
      "target_persona": [
        "analytics_engineer",
        "data_engineer"
      ],
      "company_size_fit": [
        "startup",
        "scaleup",
        "mid_market",
        "enterprise"
      ],
      "warehouse_native_support": [
        "postgres",
        "snowflake",
        "bigquery",
        "duckdb",
        "trino",
        "databricks"
      ],
      "dbt_integration": "native",
      "airflow_integration": "none",
      "openlineage_support": "none",
      "api_access": "none",
      "pricing_model": "free_forever",
      "published_pricing": true,
      "pricing_starts_at_usd": 0,
      "pricing_unit": "custom",
      "has_free_tier": true,
      "has_oss_self_host": true,
      "quality_testing": {
        "test_authoring": "yaml",
        "test_paradigm": "assertion_based",
        "ml_anomaly_detection": false,
        "ml_training_window": null,
        "root_cause_analysis": false,
        "incident_management": false,
        "circuit_breaker_support": false,
        "freshness_monitoring": true,
        "volume_monitoring": true,
        "schema_change_detection": true,
        "column_level_profiling": false,
        "custom_sql_checks": true,
        "data_contracts_enforcement": false,
        "monitors_at": [
          "warehouse_table",
          "warehouse_column",
          "dbt_model"
        ],
        "dbt_native": true,
        "dbt_test_compatible": true,
        "runs_in_ci": true,
        "runs_pre_merge": true,
        "alerting_channels": []
      },
      "catalog_discovery": null,
      "lineage_metadata": null,
      "key_features": [
        "dbt-native-testing",
        "assertion-based-testing",
        "warehouse-native-monitoring",
        "schema-change-detection"
      ],
      "notable_missing": [
        "ml-anomaly-detection",
        "column-level-lineage",
        "data-contracts"
      ],
      "common_alternatives": [
        "great-expectations",
        "soda",
        "elementary",
        "datafold"
      ],
      "one_liner": "Open-source dbt package adding 50+ Great Expectations-style assertions as native dbt tests that run in your own warehouse.",
      "last_verified": "2026-05-30"
    },
    {
      "slug": "elementary",
      "url": "https://datastackindex.com/data-observability/tools/elementary/",
      "name": "Elementary",
      "vendor": "Elementary Data",
      "homepage": "https://www.elementary-data.com",
      "repo": "https://github.com/elementary-data/elementary",
      "docs_url": "https://docs.elementary-data.com",
      "founded_year": 2021,
      "headquarters": "Tel Aviv, Israel",
      "status": "active",
      "primary_cluster": "quality_testing",
      "cluster_strength": {
        "quality_testing": 3,
        "catalog_discovery": 0,
        "lineage_metadata": 2
      },
      "deployment": "both",
      "license_type": "open_source",
      "license_spdx": "Apache-2.0",
      "target_persona": [
        "analytics_engineer",
        "data_engineer"
      ],
      "company_size_fit": [
        "startup",
        "scaleup",
        "mid_market"
      ],
      "warehouse_native_support": [
        "bigquery",
        "snowflake",
        "redshift",
        "databricks",
        "postgres",
        "clickhouse"
      ],
      "dbt_integration": "native",
      "airflow_integration": "plugin",
      "openlineage_support": "none",
      "api_access": "full",
      "pricing_model": "open_core",
      "published_pricing": false,
      "pricing_starts_at_usd": null,
      "pricing_unit": "per_seat",
      "has_free_tier": true,
      "has_oss_self_host": true,
      "quality_testing": {
        "test_authoring": "yaml",
        "test_paradigm": "both",
        "ml_anomaly_detection": true,
        "ml_training_window": "14 days minimum, 30 days recommended",
        "root_cause_analysis": true,
        "incident_management": true,
        "circuit_breaker_support": false,
        "freshness_monitoring": true,
        "volume_monitoring": true,
        "schema_change_detection": true,
        "column_level_profiling": true,
        "custom_sql_checks": true,
        "data_contracts_enforcement": false,
        "monitors_at": [
          "dbt_model",
          "warehouse_table",
          "warehouse_column"
        ],
        "dbt_native": true,
        "dbt_test_compatible": true,
        "runs_in_ci": true,
        "runs_pre_merge": false,
        "alerting_channels": [
          "slack",
          "teams",
          "pagerduty",
          "email",
          "webhook"
        ]
      },
      "catalog_discovery": null,
      "lineage_metadata": {
        "lineage_granularity": "both",
        "lineage_extraction_method": [
          "dbt_manifest",
          "sql_static_analysis"
        ],
        "cross_system_lineage": false,
        "bi_tool_lineage": [],
        "upstream_source_lineage": false,
        "impact_analysis": true,
        "reverse_impact_analysis": false,
        "openlineage_conformance": "none",
        "historical_lineage": true,
        "lineage_api": true,
        "lineage_diff": false
      },
      "key_features": [
        "dbt-native-testing",
        "assertion-based-testing",
        "ml-anomaly-detection",
        "schema-change-detection",
        "column-level-lineage"
      ],
      "notable_missing": [
        "circuit-breaker",
        "openlineage-native",
        "pre-merge-diffing"
      ],
      "common_alternatives": [
        "monte-carlo",
        "datafold"
      ],
      "one_liner": "The dbt-native observability layer — tests, anomaly detection, and lineage that live inside your dbt project.",
      "last_verified": "2026-04-25"
    },
    {
      "slug": "great-expectations",
      "url": "https://datastackindex.com/data-observability/tools/great-expectations/",
      "name": "Great Expectations",
      "vendor": "Great Expectations",
      "homepage": "https://greatexpectations.io",
      "repo": "https://github.com/great-expectations/great_expectations",
      "docs_url": "https://docs.greatexpectations.io",
      "founded_year": 2017,
      "headquarters": null,
      "status": "acquired",
      "primary_cluster": "quality_testing",
      "cluster_strength": {
        "quality_testing": 3,
        "catalog_discovery": 0,
        "lineage_metadata": 0
      },
      "deployment": "both",
      "license_type": "open_source",
      "license_spdx": "Apache-2.0",
      "target_persona": [
        "data_engineer",
        "analytics_engineer",
        "platform_engineer"
      ],
      "company_size_fit": [
        "startup",
        "scaleup",
        "mid_market",
        "enterprise"
      ],
      "warehouse_native_support": [
        "snowflake",
        "bigquery",
        "redshift",
        "databricks",
        "postgres",
        "mysql",
        "mssql",
        "fabric"
      ],
      "dbt_integration": "none",
      "airflow_integration": "native",
      "openlineage_support": "none",
      "api_access": "full",
      "pricing_model": "open_core",
      "published_pricing": false,
      "pricing_starts_at_usd": null,
      "pricing_unit": "custom",
      "has_free_tier": true,
      "has_oss_self_host": true,
      "quality_testing": {
        "test_authoring": "python",
        "test_paradigm": "assertion_based",
        "ml_anomaly_detection": false,
        "ml_training_window": null,
        "root_cause_analysis": false,
        "incident_management": false,
        "circuit_breaker_support": true,
        "freshness_monitoring": false,
        "volume_monitoring": true,
        "schema_change_detection": true,
        "column_level_profiling": true,
        "custom_sql_checks": true,
        "data_contracts_enforcement": false,
        "monitors_at": [
          "warehouse_table",
          "warehouse_column",
          "file_object"
        ],
        "dbt_native": false,
        "dbt_test_compatible": false,
        "runs_in_ci": true,
        "runs_pre_merge": false,
        "alerting_channels": [
          "slack",
          "email",
          "webhook",
          "pagerduty",
          "opsgenie",
          "teams"
        ]
      },
      "catalog_discovery": null,
      "lineage_metadata": null,
      "key_features": [
        "assertion-based-testing",
        "schema-change-detection",
        "warehouse-native-monitoring"
      ],
      "notable_missing": [
        "ml-anomaly-detection",
        "dbt-native-testing",
        "openlineage-native",
        "column-level-lineage"
      ],
      "common_alternatives": [
        "soda",
        "datafold",
        "elementary",
        "anomalo"
      ],
      "one_liner": "Python-native data validation framework — the OSS standard, now in stewardship transition after the May 2026 acquisition.",
      "last_verified": "2026-05-08"
    },
    {
      "slug": "ibm-manta",
      "url": "https://datastackindex.com/data-observability/tools/ibm-manta/",
      "name": "IBM Manta Data Lineage",
      "vendor": "IBM",
      "homepage": "https://www.ibm.com/products/manta-data-lineage",
      "repo": null,
      "docs_url": "https://www.ibm.com/docs/en/watsonxdata/standard/2.1.x?topic=components-manta-data-lineage",
      "founded_year": 2016,
      "headquarters": "Armonk, NY",
      "status": "acquired",
      "primary_cluster": "lineage_metadata",
      "cluster_strength": {
        "quality_testing": 0,
        "catalog_discovery": 2,
        "lineage_metadata": 3
      },
      "deployment": "both",
      "license_type": "proprietary",
      "license_spdx": null,
      "target_persona": [
        "data_steward",
        "governance_lead",
        "chief_data_officer",
        "data_engineer"
      ],
      "company_size_fit": [
        "enterprise"
      ],
      "warehouse_native_support": [
        "snowflake",
        "redshift",
        "bigquery",
        "databricks",
        "postgres",
        "mssql",
        "synapse"
      ],
      "dbt_integration": "metadata_sync",
      "airflow_integration": "metadata_sync",
      "openlineage_support": "consumer",
      "api_access": "full",
      "pricing_model": "enterprise_only",
      "published_pricing": false,
      "pricing_starts_at_usd": null,
      "pricing_unit": "custom",
      "has_free_tier": false,
      "has_oss_self_host": false,
      "quality_testing": null,
      "catalog_discovery": {
        "asset_types_supported": [
          "tables",
          "columns",
          "dashboards",
          "reports",
          "dbt_models",
          "glossary_terms",
          "pipelines"
        ],
        "metadata_ingestion": "crawlers",
        "connector_count": 50,
        "search_approach": "keyword",
        "natural_language_search": false,
        "business_glossary": true,
        "glossary_linking_to_assets": true,
        "ownership_tracking": true,
        "data_contracts": false,
        "governance_workflows": true,
        "access_request_workflow": true,
        "pii_auto_classification": true,
        "tag_propagation": true,
        "collaboration_features": [
          "comments",
          "wiki"
        ],
        "free_self_hosted_available": false,
        "managed_version_of_oss": null
      },
      "lineage_metadata": {
        "lineage_granularity": "both",
        "lineage_extraction_method": [
          "sql_static_analysis",
          "query_log_parsing",
          "plugin_instrumentation",
          "openlineage_events"
        ],
        "cross_system_lineage": true,
        "bi_tool_lineage": [
          "tableau",
          "powerbi",
          "cognos",
          "microstrategy",
          "qlik",
          "sas-vi",
          "looker"
        ],
        "upstream_source_lineage": true,
        "impact_analysis": true,
        "reverse_impact_analysis": true,
        "openlineage_conformance": "consumer",
        "historical_lineage": true,
        "lineage_api": true,
        "lineage_diff": false
      },
      "key_features": [
        "column-level-lineage",
        "table-level-lineage",
        "transformation-lineage",
        "reverse-impact-analysis",
        "business-glossary"
      ],
      "notable_missing": [
        "openlineage-native",
        "pre-merge-diffing",
        "ml-anomaly-detection"
      ],
      "common_alternatives": [
        "atlan",
        "datahub"
      ],
      "one_liner": "The deepest scanner-driven lineage product on the market — built for legacy estates (SAP, Cognos, Informatica) modern catalogs miss.",
      "last_verified": "2026-05-08"
    },
    {
      "slug": "marquez",
      "url": "https://datastackindex.com/data-observability/tools/marquez/",
      "name": "Marquez",
      "vendor": "Marquez Project",
      "homepage": "https://marquezproject.ai",
      "repo": "https://github.com/MarquezProject/marquez",
      "docs_url": "https://marquezproject.ai",
      "founded_year": 2018,
      "headquarters": null,
      "status": "active",
      "primary_cluster": "lineage_metadata",
      "cluster_strength": {
        "quality_testing": 0,
        "catalog_discovery": 1,
        "lineage_metadata": 3
      },
      "deployment": "self_hosted",
      "license_type": "open_source",
      "license_spdx": "Apache-2.0",
      "target_persona": [
        "data_engineer",
        "platform_engineer"
      ],
      "company_size_fit": [
        "scaleup",
        "mid_market",
        "enterprise"
      ],
      "warehouse_native_support": [],
      "dbt_integration": "plugin",
      "airflow_integration": "plugin",
      "openlineage_support": "native",
      "api_access": "full",
      "pricing_model": "free_forever",
      "published_pricing": true,
      "pricing_starts_at_usd": 0,
      "pricing_unit": "custom",
      "has_free_tier": true,
      "has_oss_self_host": true,
      "quality_testing": null,
      "catalog_discovery": {
        "asset_types_supported": [
          "dbt_models",
          "pipelines",
          "tables"
        ],
        "metadata_ingestion": "push_api",
        "connector_count": null,
        "search_approach": "keyword",
        "natural_language_search": false,
        "business_glossary": false,
        "glossary_linking_to_assets": false,
        "ownership_tracking": false,
        "data_contracts": false,
        "governance_workflows": false,
        "access_request_workflow": false,
        "pii_auto_classification": false,
        "tag_propagation": false,
        "collaboration_features": [],
        "free_self_hosted_available": true,
        "managed_version_of_oss": null
      },
      "lineage_metadata": {
        "lineage_granularity": "both",
        "lineage_extraction_method": [
          "openlineage_events",
          "api_push"
        ],
        "cross_system_lineage": true,
        "bi_tool_lineage": [],
        "upstream_source_lineage": true,
        "impact_analysis": true,
        "reverse_impact_analysis": false,
        "openlineage_conformance": "consumer",
        "historical_lineage": true,
        "lineage_api": true,
        "lineage_diff": false
      },
      "key_features": [
        "openlineage-native",
        "column-level-lineage",
        "table-level-lineage",
        "transformation-lineage"
      ],
      "notable_missing": [
        "business-glossary",
        "pii-auto-classification",
        "reverse-impact-analysis"
      ],
      "common_alternatives": [
        "datahub",
        "openmetadata",
        "atlan"
      ],
      "one_liner": "The OpenLineage reference backend — vendor-neutral lineage events from Spark, Airflow, dbt, and Flink, stored and visualised.",
      "last_verified": "2026-05-08"
    },
    {
      "slug": "metaplane",
      "url": "https://datastackindex.com/data-observability/tools/metaplane/",
      "name": "Metaplane",
      "vendor": "Metaplane (Datadog)",
      "homepage": "https://www.metaplane.dev",
      "repo": null,
      "docs_url": "https://docs.metaplane.dev",
      "founded_year": 2019,
      "headquarters": "Boston, MA",
      "status": "acquired",
      "primary_cluster": "quality_testing",
      "cluster_strength": {
        "quality_testing": 3,
        "catalog_discovery": 0,
        "lineage_metadata": 2
      },
      "deployment": "saas",
      "license_type": "proprietary",
      "license_spdx": null,
      "target_persona": [
        "analytics_engineer",
        "data_engineer",
        "platform_engineer"
      ],
      "company_size_fit": [
        "startup",
        "scaleup",
        "mid_market"
      ],
      "warehouse_native_support": [
        "snowflake",
        "bigquery",
        "redshift",
        "databricks",
        "postgres",
        "mysql",
        "mssql",
        "clickhouse"
      ],
      "dbt_integration": "native",
      "airflow_integration": "metadata_sync",
      "openlineage_support": "none",
      "api_access": "full",
      "pricing_model": "per_table_monitored",
      "published_pricing": true,
      "pricing_starts_at_usd": null,
      "pricing_unit": "per_table_monitored",
      "has_free_tier": true,
      "has_oss_self_host": false,
      "quality_testing": {
        "test_authoring": "gui",
        "test_paradigm": "both",
        "ml_anomaly_detection": true,
        "ml_training_window": "Learns historical patterns including seasonality and trend; alerts can fire within days of connection",
        "root_cause_analysis": true,
        "incident_management": true,
        "circuit_breaker_support": false,
        "freshness_monitoring": true,
        "volume_monitoring": true,
        "schema_change_detection": true,
        "column_level_profiling": true,
        "custom_sql_checks": true,
        "data_contracts_enforcement": false,
        "monitors_at": [
          "warehouse_table",
          "warehouse_column",
          "dbt_model",
          "pipeline_task",
          "bi_dashboard"
        ],
        "dbt_native": true,
        "dbt_test_compatible": true,
        "runs_in_ci": true,
        "runs_pre_merge": true,
        "alerting_channels": [
          "slack",
          "email",
          "teams",
          "pagerduty",
          "jira",
          "webhook"
        ]
      },
      "catalog_discovery": null,
      "lineage_metadata": {
        "lineage_granularity": "both",
        "lineage_extraction_method": [
          "query_log_parsing",
          "dbt_manifest"
        ],
        "cross_system_lineage": true,
        "bi_tool_lineage": [
          "looker",
          "tableau",
          "metabase",
          "mode",
          "sigma",
          "power-bi"
        ],
        "upstream_source_lineage": true,
        "impact_analysis": true,
        "reverse_impact_analysis": true,
        "openlineage_conformance": "none",
        "historical_lineage": false,
        "lineage_api": false,
        "lineage_diff": false
      },
      "key_features": [
        "ml-anomaly-detection",
        "column-level-lineage",
        "schema-change-detection",
        "warehouse-native-monitoring",
        "dbt-native-testing"
      ],
      "notable_missing": [
        "openlineage-native",
        "business-glossary",
        "data-contracts",
        "circuit-breaker"
      ],
      "common_alternatives": [
        "monte-carlo",
        "elementary",
        "bigeye",
        "anomalo",
        "datafold"
      ],
      "one_liner": "ML-powered, no-code data observability for the dbt and warehouse stack with automatic column-level lineage — now Metaplane by Datadog.",
      "last_verified": "2026-05-30"
    },
    {
      "slug": "monte-carlo",
      "url": "https://datastackindex.com/data-observability/tools/monte-carlo/",
      "name": "Monte Carlo",
      "vendor": "Monte Carlo Data",
      "homepage": "https://www.montecarlodata.com",
      "repo": null,
      "docs_url": "https://docs.getmontecarlo.com",
      "founded_year": 2019,
      "headquarters": "San Francisco, CA",
      "status": "active",
      "primary_cluster": "quality_testing",
      "cluster_strength": {
        "quality_testing": 3,
        "catalog_discovery": 2,
        "lineage_metadata": 3
      },
      "deployment": "saas",
      "license_type": "proprietary",
      "license_spdx": null,
      "target_persona": [
        "data_engineer",
        "platform_engineer",
        "chief_data_officer"
      ],
      "company_size_fit": [
        "mid_market",
        "enterprise"
      ],
      "warehouse_native_support": [
        "bigquery",
        "snowflake",
        "redshift",
        "databricks",
        "postgres",
        "mysql",
        "mssql",
        "clickhouse",
        "athena",
        "fabric"
      ],
      "dbt_integration": "native",
      "airflow_integration": "native",
      "openlineage_support": "none",
      "api_access": "full",
      "pricing_model": "usage_based",
      "published_pricing": false,
      "pricing_starts_at_usd": null,
      "pricing_unit": "custom",
      "has_free_tier": false,
      "has_oss_self_host": false,
      "quality_testing": {
        "test_authoring": "code_first_plus_gui",
        "test_paradigm": "both",
        "ml_anomaly_detection": true,
        "ml_training_window": "automatic, typically 2-4 weeks of historical data",
        "root_cause_analysis": true,
        "incident_management": true,
        "circuit_breaker_support": true,
        "freshness_monitoring": true,
        "volume_monitoring": true,
        "schema_change_detection": true,
        "column_level_profiling": true,
        "custom_sql_checks": true,
        "data_contracts_enforcement": false,
        "monitors_at": [
          "warehouse_table",
          "warehouse_column",
          "dbt_model",
          "pipeline_task",
          "bi_dashboard",
          "ml_feature"
        ],
        "dbt_native": false,
        "dbt_test_compatible": true,
        "runs_in_ci": false,
        "runs_pre_merge": false,
        "alerting_channels": [
          "slack",
          "teams",
          "pagerduty",
          "email",
          "webhook",
          "opsgenie",
          "jira"
        ]
      },
      "catalog_discovery": {
        "asset_types_supported": [
          "tables",
          "columns",
          "dbt_models",
          "dashboards",
          "reports",
          "pipelines"
        ],
        "metadata_ingestion": "pull_connectors",
        "connector_count": null,
        "search_approach": "hybrid",
        "natural_language_search": true,
        "business_glossary": false,
        "glossary_linking_to_assets": false,
        "ownership_tracking": true,
        "data_contracts": false,
        "governance_workflows": false,
        "access_request_workflow": false,
        "pii_auto_classification": false,
        "tag_propagation": true,
        "collaboration_features": [
          "slack_integration"
        ],
        "free_self_hosted_available": false,
        "managed_version_of_oss": null
      },
      "lineage_metadata": {
        "lineage_granularity": "both",
        "lineage_extraction_method": [
          "query_log_parsing",
          "dbt_manifest",
          "sql_static_analysis"
        ],
        "cross_system_lineage": true,
        "bi_tool_lineage": [
          "looker",
          "tableau",
          "power-bi",
          "mode"
        ],
        "upstream_source_lineage": true,
        "impact_analysis": true,
        "reverse_impact_analysis": true,
        "openlineage_conformance": "none",
        "historical_lineage": true,
        "lineage_api": true,
        "lineage_diff": false
      },
      "key_features": [
        "ml-anomaly-detection",
        "assertion-based-testing",
        "schema-change-detection",
        "warehouse-native-monitoring",
        "column-level-lineage",
        "circuit-breaker"
      ],
      "notable_missing": [
        "dbt-native-testing",
        "openlineage-native",
        "pre-merge-diffing",
        "business-glossary"
      ],
      "common_alternatives": [
        "elementary",
        "datafold"
      ],
      "one_liner": "Warehouse-side data observability for teams whose problems are upstream of dbt — ingestion, streaming, and across the full pipeline.",
      "last_verified": "2026-04-25"
    },
    {
      "slug": "openmetadata",
      "url": "https://datastackindex.com/data-observability/tools/openmetadata/",
      "name": "OpenMetadata",
      "vendor": "Collate",
      "homepage": "https://open-metadata.org",
      "repo": "https://github.com/open-metadata/OpenMetadata",
      "docs_url": "https://docs.open-metadata.org",
      "founded_year": 2021,
      "headquarters": "Saratoga, CA",
      "status": "active",
      "primary_cluster": "catalog_discovery",
      "cluster_strength": {
        "quality_testing": 2,
        "catalog_discovery": 3,
        "lineage_metadata": 3
      },
      "deployment": "both",
      "license_type": "open_source",
      "license_spdx": "Apache-2.0",
      "target_persona": [
        "data_engineer",
        "platform_engineer",
        "data_steward",
        "analytics_engineer",
        "governance_lead"
      ],
      "company_size_fit": [
        "startup",
        "scaleup",
        "mid_market",
        "enterprise"
      ],
      "warehouse_native_support": [
        "snowflake",
        "bigquery",
        "redshift",
        "databricks",
        "postgres",
        "mysql",
        "mssql",
        "clickhouse",
        "trino",
        "athena",
        "synapse"
      ],
      "dbt_integration": "native",
      "airflow_integration": "native",
      "openlineage_support": "none",
      "api_access": "full",
      "pricing_model": "open_core",
      "published_pricing": false,
      "pricing_starts_at_usd": null,
      "pricing_unit": "custom",
      "has_free_tier": true,
      "has_oss_self_host": true,
      "quality_testing": {
        "test_authoring": "code_first_plus_gui",
        "test_paradigm": "both",
        "ml_anomaly_detection": false,
        "ml_training_window": null,
        "root_cause_analysis": false,
        "incident_management": true,
        "circuit_breaker_support": false,
        "freshness_monitoring": true,
        "volume_monitoring": true,
        "schema_change_detection": true,
        "column_level_profiling": true,
        "custom_sql_checks": true,
        "data_contracts_enforcement": true,
        "monitors_at": [
          "warehouse_table",
          "warehouse_column",
          "dbt_model"
        ],
        "dbt_native": true,
        "dbt_test_compatible": true,
        "runs_in_ci": false,
        "runs_pre_merge": false,
        "alerting_channels": [
          "slack",
          "email",
          "webhook",
          "teams"
        ]
      },
      "catalog_discovery": {
        "asset_types_supported": [
          "tables",
          "columns",
          "dashboards",
          "reports",
          "dbt_models",
          "dbt_metrics",
          "dbt_sources",
          "ml_features",
          "ml_models",
          "pipelines",
          "topics",
          "files",
          "api_endpoints",
          "glossary_terms"
        ],
        "metadata_ingestion": "pull_connectors",
        "connector_count": 120,
        "search_approach": "hybrid",
        "natural_language_search": true,
        "business_glossary": true,
        "glossary_linking_to_assets": true,
        "ownership_tracking": true,
        "data_contracts": true,
        "governance_workflows": true,
        "access_request_workflow": true,
        "pii_auto_classification": true,
        "tag_propagation": true,
        "collaboration_features": [
          "comments",
          "q_and_a",
          "slack_integration"
        ],
        "free_self_hosted_available": true,
        "managed_version_of_oss": null
      },
      "lineage_metadata": {
        "lineage_granularity": "column_level",
        "lineage_extraction_method": [
          "sql_static_analysis",
          "query_log_parsing",
          "dbt_manifest",
          "plugin_instrumentation",
          "api_push"
        ],
        "cross_system_lineage": true,
        "bi_tool_lineage": [
          "tableau",
          "looker",
          "powerbi",
          "superset",
          "metabase",
          "mode",
          "sigma",
          "lightdash"
        ],
        "upstream_source_lineage": true,
        "impact_analysis": true,
        "reverse_impact_analysis": true,
        "openlineage_conformance": "none",
        "historical_lineage": true,
        "lineage_api": true,
        "lineage_diff": false
      },
      "key_features": [
        "column-level-lineage",
        "business-glossary",
        "data-contracts",
        "pii-auto-classification",
        "schema-change-detection"
      ],
      "notable_missing": [
        "openlineage-native",
        "pre-merge-diffing",
        "ml-anomaly-detection"
      ],
      "common_alternatives": [
        "datahub",
        "atlan",
        "amundsen",
        "apache-atlas"
      ],
      "one_liner": "Apache-2.0 unified metadata platform with a deliberately simple stack — discovery, lineage, quality, and contracts in one project.",
      "last_verified": "2026-05-08"
    },
    {
      "slug": "secoda",
      "url": "https://datastackindex.com/data-observability/tools/secoda/",
      "name": "Secoda",
      "vendor": "Secoda (Atlassian)",
      "homepage": "https://www.secoda.co",
      "repo": null,
      "docs_url": "https://docs.secoda.co",
      "founded_year": 2021,
      "headquarters": "Toronto, Ontario, Canada",
      "status": "acquired",
      "primary_cluster": "catalog_discovery",
      "cluster_strength": {
        "quality_testing": 0,
        "catalog_discovery": 3,
        "lineage_metadata": 3
      },
      "deployment": "both",
      "license_type": "proprietary",
      "license_spdx": null,
      "target_persona": [
        "data_steward",
        "analyst",
        "data_engineer",
        "analytics_engineer",
        "governance_lead"
      ],
      "company_size_fit": [
        "startup",
        "scaleup",
        "mid_market",
        "enterprise"
      ],
      "warehouse_native_support": [
        "snowflake",
        "bigquery",
        "redshift",
        "databricks",
        "postgres",
        "mysql",
        "mssql",
        "motherduck"
      ],
      "dbt_integration": "native",
      "airflow_integration": "metadata_sync",
      "openlineage_support": "none",
      "api_access": "partial",
      "pricing_model": "per_seat_tiered",
      "published_pricing": false,
      "pricing_starts_at_usd": null,
      "pricing_unit": "per_seat",
      "has_free_tier": false,
      "has_oss_self_host": false,
      "quality_testing": null,
      "catalog_discovery": {
        "asset_types_supported": [
          "tables",
          "columns",
          "dashboards",
          "reports",
          "dbt_models",
          "dbt_sources",
          "glossary_terms"
        ],
        "metadata_ingestion": "both",
        "connector_count": 50,
        "search_approach": "llm_native",
        "natural_language_search": true,
        "business_glossary": true,
        "glossary_linking_to_assets": true,
        "ownership_tracking": true,
        "data_contracts": false,
        "governance_workflows": true,
        "access_request_workflow": true,
        "pii_auto_classification": true,
        "tag_propagation": true,
        "collaboration_features": [
          "q_and_a",
          "slack_integration",
          "comments"
        ],
        "free_self_hosted_available": false,
        "managed_version_of_oss": null
      },
      "lineage_metadata": {
        "lineage_granularity": "both",
        "lineage_extraction_method": [
          "query_log_parsing",
          "dbt_manifest",
          "api_push"
        ],
        "cross_system_lineage": true,
        "bi_tool_lineage": [
          "tableau",
          "looker",
          "power-bi",
          "mode",
          "metabase",
          "sigma"
        ],
        "upstream_source_lineage": true,
        "impact_analysis": true,
        "reverse_impact_analysis": true,
        "openlineage_conformance": "none",
        "historical_lineage": false,
        "lineage_api": true,
        "lineage_diff": false
      },
      "key_features": [
        "business-glossary",
        "column-level-lineage",
        "pii-auto-classification",
        "table-level-lineage",
        "reverse-impact-analysis",
        "transformation-lineage"
      ],
      "notable_missing": [
        "openlineage-native",
        "data-contracts",
        "circuit-breaker",
        "ml-anomaly-detection"
      ],
      "common_alternatives": [
        "atlan",
        "datahub",
        "openmetadata",
        "unity-catalog",
        "select-star"
      ],
      "one_liner": "AI-native data catalog, lineage, and observability from Toronto — acquired by Atlassian in December 2025 to power Rovo AI.",
      "last_verified": "2026-05-30"
    },
    {
      "slug": "select-star",
      "url": "https://datastackindex.com/data-observability/tools/select-star/",
      "name": "Select Star",
      "vendor": "Select Star (Snowflake)",
      "homepage": "https://www.selectstar.com",
      "repo": null,
      "docs_url": "https://docs.selectstar.com",
      "founded_year": 2020,
      "headquarters": "San Francisco, California, United States",
      "status": "acquired",
      "primary_cluster": "catalog_discovery",
      "cluster_strength": {
        "quality_testing": 0,
        "catalog_discovery": 3,
        "lineage_metadata": 2
      },
      "deployment": "saas",
      "license_type": "proprietary",
      "license_spdx": null,
      "target_persona": [
        "data_engineer",
        "analytics_engineer",
        "analyst",
        "data_steward",
        "governance_lead"
      ],
      "company_size_fit": [
        "scaleup",
        "mid_market",
        "enterprise"
      ],
      "warehouse_native_support": [
        "snowflake",
        "bigquery",
        "redshift",
        "databricks",
        "postgres",
        "mysql",
        "mssql"
      ],
      "dbt_integration": "native",
      "airflow_integration": "metadata_sync",
      "openlineage_support": "consumer",
      "api_access": "partial",
      "pricing_model": "enterprise_only",
      "published_pricing": false,
      "pricing_starts_at_usd": null,
      "pricing_unit": "custom",
      "has_free_tier": false,
      "has_oss_self_host": false,
      "quality_testing": null,
      "catalog_discovery": {
        "asset_types_supported": [
          "tables",
          "columns",
          "dashboards",
          "reports",
          "dbt_models",
          "dbt_sources",
          "glossary_terms"
        ],
        "metadata_ingestion": "both",
        "connector_count": 28,
        "search_approach": "hybrid",
        "natural_language_search": true,
        "business_glossary": true,
        "glossary_linking_to_assets": true,
        "ownership_tracking": true,
        "data_contracts": false,
        "governance_workflows": true,
        "access_request_workflow": false,
        "pii_auto_classification": true,
        "tag_propagation": true,
        "collaboration_features": [
          "comments",
          "slack_integration"
        ],
        "free_self_hosted_available": false,
        "managed_version_of_oss": null
      },
      "lineage_metadata": {
        "lineage_granularity": "both",
        "lineage_extraction_method": [
          "query_log_parsing",
          "dbt_manifest",
          "openlineage_events"
        ],
        "cross_system_lineage": true,
        "bi_tool_lineage": [
          "tableau",
          "power-bi",
          "looker",
          "mode",
          "sigma",
          "metabase",
          "thoughtspot",
          "quicksight",
          "hex"
        ],
        "upstream_source_lineage": true,
        "impact_analysis": true,
        "reverse_impact_analysis": true,
        "openlineage_conformance": "consumer",
        "historical_lineage": false,
        "lineage_api": true,
        "lineage_diff": false
      },
      "key_features": [
        "column-level-lineage",
        "table-level-lineage",
        "transformation-lineage",
        "business-glossary",
        "pii-auto-classification",
        "reverse-impact-analysis"
      ],
      "notable_missing": [
        "data-contracts",
        "ml-anomaly-detection",
        "circuit-breaker",
        "warehouse-native-monitoring"
      ],
      "common_alternatives": [
        "atlan",
        "secoda",
        "alation",
        "collibra",
        "datahub",
        "amundsen"
      ],
      "one_liner": "Automated data catalog with column-level lineage parsed from query logs — being acquired by Snowflake to power Horizon Catalog.",
      "last_verified": "2026-07-03"
    },
    {
      "slug": "sifflet",
      "url": "https://datastackindex.com/data-observability/tools/sifflet/",
      "name": "Sifflet",
      "vendor": "Sifflet",
      "homepage": "https://www.siffletdata.com",
      "repo": null,
      "docs_url": "https://docs.siffletdata.com/docs/overview",
      "founded_year": 2021,
      "headquarters": "Paris, France",
      "status": "active",
      "primary_cluster": "quality_testing",
      "cluster_strength": {
        "quality_testing": 3,
        "catalog_discovery": 2,
        "lineage_metadata": 3
      },
      "deployment": "both",
      "license_type": "proprietary",
      "license_spdx": null,
      "target_persona": [
        "data_engineer",
        "analytics_engineer",
        "data_steward",
        "platform_engineer",
        "chief_data_officer"
      ],
      "company_size_fit": [
        "scaleup",
        "mid_market",
        "enterprise"
      ],
      "warehouse_native_support": [
        "snowflake",
        "bigquery",
        "redshift",
        "databricks",
        "athena",
        "synapse",
        "postgres",
        "mysql",
        "mssql"
      ],
      "dbt_integration": "native",
      "airflow_integration": "plugin",
      "openlineage_support": "none",
      "api_access": "full",
      "pricing_model": "per_asset",
      "published_pricing": false,
      "pricing_starts_at_usd": null,
      "pricing_unit": "per_asset",
      "has_free_tier": false,
      "has_oss_self_host": false,
      "quality_testing": {
        "test_authoring": "code_first_plus_gui",
        "test_paradigm": "both",
        "ml_anomaly_detection": true,
        "ml_training_window": "Proprietary time-series forecasting learns historical patterns to set dynamic thresholds for freshness, volume, and distribution",
        "root_cause_analysis": true,
        "incident_management": true,
        "circuit_breaker_support": true,
        "freshness_monitoring": true,
        "volume_monitoring": true,
        "schema_change_detection": true,
        "column_level_profiling": true,
        "custom_sql_checks": true,
        "data_contracts_enforcement": false,
        "monitors_at": [
          "warehouse_table",
          "warehouse_column",
          "bi_dashboard",
          "pipeline_task"
        ],
        "dbt_native": true,
        "dbt_test_compatible": true,
        "runs_in_ci": true,
        "runs_pre_merge": true,
        "alerting_channels": [
          "slack",
          "teams",
          "email",
          "pagerduty",
          "jira",
          "webhook"
        ]
      },
      "catalog_discovery": {
        "asset_types_supported": [
          "tables",
          "dashboards",
          "pipelines"
        ],
        "metadata_ingestion": "pull_connectors",
        "connector_count": 32,
        "search_approach": "keyword",
        "natural_language_search": true,
        "business_glossary": true,
        "glossary_linking_to_assets": true,
        "ownership_tracking": true,
        "data_contracts": false,
        "governance_workflows": true,
        "access_request_workflow": false,
        "pii_auto_classification": false,
        "tag_propagation": true,
        "collaboration_features": [
          "slack_integration"
        ],
        "free_self_hosted_available": false,
        "managed_version_of_oss": null
      },
      "lineage_metadata": {
        "lineage_granularity": "both",
        "lineage_extraction_method": [
          "query_log_parsing",
          "dbt_manifest",
          "api_push"
        ],
        "cross_system_lineage": true,
        "bi_tool_lineage": [
          "tableau",
          "power-bi",
          "looker",
          "qlik",
          "microstrategy",
          "quicksight"
        ],
        "upstream_source_lineage": true,
        "impact_analysis": true,
        "reverse_impact_analysis": true,
        "openlineage_conformance": "none",
        "historical_lineage": false,
        "lineage_api": true,
        "lineage_diff": false
      },
      "key_features": [
        "ml-anomaly-detection",
        "column-level-lineage",
        "circuit-breaker",
        "warehouse-native-monitoring",
        "business-glossary",
        "reverse-impact-analysis"
      ],
      "notable_missing": [
        "openlineage-native",
        "data-contracts",
        "pii-auto-classification",
        "pre-merge-diffing"
      ],
      "common_alternatives": [
        "monte-carlo",
        "bigeye",
        "anomalo",
        "soda"
      ],
      "one_liner": "EU-built full-stack data observability pairing ML-driven monitoring with an embedded catalog and field-level lineage.",
      "last_verified": "2026-05-30"
    },
    {
      "slug": "soda",
      "url": "https://datastackindex.com/data-observability/tools/soda/",
      "name": "Soda",
      "vendor": "Soda Data",
      "homepage": "https://www.soda.io",
      "repo": "https://github.com/sodadata/soda-core",
      "docs_url": "https://docs.soda.io",
      "founded_year": 2019,
      "headquarters": "Brussels, Belgium",
      "status": "active",
      "primary_cluster": "quality_testing",
      "cluster_strength": {
        "quality_testing": 3,
        "catalog_discovery": 0,
        "lineage_metadata": 0
      },
      "deployment": "both",
      "license_type": "source_available",
      "license_spdx": "Elastic-2.0",
      "target_persona": [
        "data_engineer",
        "analytics_engineer",
        "platform_engineer",
        "data_steward",
        "governance_lead"
      ],
      "company_size_fit": [
        "scaleup",
        "mid_market",
        "enterprise"
      ],
      "warehouse_native_support": [
        "snowflake",
        "bigquery",
        "redshift",
        "databricks",
        "postgres",
        "mysql",
        "mssql",
        "duckdb",
        "athena",
        "trino",
        "synapse",
        "fabric"
      ],
      "dbt_integration": "metadata_sync",
      "airflow_integration": "native",
      "openlineage_support": "none",
      "api_access": "full",
      "pricing_model": "per_seat_tiered",
      "published_pricing": true,
      "pricing_starts_at_usd": 750,
      "pricing_unit": "custom",
      "has_free_tier": true,
      "has_oss_self_host": false,
      "quality_testing": {
        "test_authoring": "code_first_plus_gui",
        "test_paradigm": "both",
        "ml_anomaly_detection": true,
        "ml_training_window": null,
        "root_cause_analysis": true,
        "incident_management": true,
        "circuit_breaker_support": true,
        "freshness_monitoring": true,
        "volume_monitoring": true,
        "schema_change_detection": true,
        "column_level_profiling": true,
        "custom_sql_checks": true,
        "data_contracts_enforcement": true,
        "monitors_at": [
          "warehouse_table",
          "warehouse_column",
          "dbt_model"
        ],
        "dbt_native": false,
        "dbt_test_compatible": true,
        "runs_in_ci": true,
        "runs_pre_merge": false,
        "alerting_channels": [
          "slack",
          "teams",
          "email",
          "webhook",
          "pagerduty",
          "opsgenie",
          "jira"
        ]
      },
      "catalog_discovery": null,
      "lineage_metadata": null,
      "key_features": [
        "assertion-based-testing",
        "ml-anomaly-detection",
        "data-contracts",
        "schema-change-detection",
        "warehouse-native-monitoring"
      ],
      "notable_missing": [
        "column-level-lineage",
        "pre-merge-diffing",
        "openlineage-native"
      ],
      "common_alternatives": [
        "great-expectations",
        "monte-carlo",
        "anomalo",
        "bigeye"
      ],
      "one_liner": "YAML-first data contracts and observability — SodaCL plus Soda Cloud, with anomaly detection and a self-hosted Kubernetes runner.",
      "last_verified": "2026-05-08"
    },
    {
      "slug": "unity-catalog",
      "url": "https://datastackindex.com/data-observability/tools/unity-catalog/",
      "name": "Unity Catalog",
      "vendor": "Databricks",
      "homepage": "https://www.unitycatalog.io",
      "repo": "https://github.com/unitycatalog/unitycatalog",
      "docs_url": "https://docs.unitycatalog.io",
      "founded_year": 2024,
      "headquarters": "San Francisco, CA",
      "status": "active",
      "primary_cluster": "catalog_discovery",
      "cluster_strength": {
        "quality_testing": 0,
        "catalog_discovery": 2,
        "lineage_metadata": 0
      },
      "deployment": "self_hosted",
      "license_type": "open_source",
      "license_spdx": "Apache-2.0",
      "target_persona": [
        "data_engineer",
        "platform_engineer",
        "ml_engineer"
      ],
      "company_size_fit": [
        "scaleup",
        "mid_market",
        "enterprise"
      ],
      "warehouse_native_support": [
        "databricks",
        "trino",
        "athena",
        "snowflake",
        "bigquery",
        "duckdb"
      ],
      "dbt_integration": "plugin",
      "airflow_integration": "api_only",
      "openlineage_support": "none",
      "api_access": "full",
      "pricing_model": "free_forever",
      "published_pricing": true,
      "pricing_starts_at_usd": 0,
      "pricing_unit": "custom",
      "has_free_tier": true,
      "has_oss_self_host": true,
      "quality_testing": null,
      "catalog_discovery": {
        "asset_types_supported": [
          "tables",
          "files",
          "ml_models",
          "api_endpoints"
        ],
        "metadata_ingestion": "push_api",
        "connector_count": null,
        "search_approach": "keyword",
        "natural_language_search": false,
        "business_glossary": false,
        "glossary_linking_to_assets": false,
        "ownership_tracking": true,
        "data_contracts": false,
        "governance_workflows": false,
        "access_request_workflow": false,
        "pii_auto_classification": false,
        "tag_propagation": false,
        "collaboration_features": [],
        "free_self_hosted_available": true,
        "managed_version_of_oss": null
      },
      "lineage_metadata": null,
      "key_features": [
        "table-level-lineage"
      ],
      "notable_missing": [
        "column-level-lineage",
        "business-glossary",
        "openlineage-native",
        "pii-auto-classification"
      ],
      "common_alternatives": [
        "datahub",
        "openmetadata"
      ],
      "one_liner": "Open-source universal catalog for data and AI under Apache-2.0 — Iceberg-REST and Hive-MS compatible, Databricks-led, LF AI hosted.",
      "last_verified": "2026-05-08"
    }
  ]
}