{"adoption": {"forks": 1204, "observed_at": "2026-08-28T04:05:34.276548+00:00", "stars": 1774}, "canonical_url": "https://ross.abutalabs.com/products/open-data-registry", "card": {"archived": false, "artifact_type": "dataset", "description": "A registry of publicly available datasets on AWS", "domain": ["data-science", "big-data", "cloud-computing", "analytics", "awesome-lists"], "enriched": true, "function": ["search-engine", "data-science", "etl"], "health_score": 80, "homepage": "https://registry.opendata.aws", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["awslabs/open-data-registry"], "name": "awslabs/open-data-registry", "platform": ["cloud", "python"], "pushed_at": "2026-08-26T13:02:33+00:00", "repo": "awslabs/open-data-registry", "stars": 1774, "tags": ["open-data", "aws-s3", "dataset-registry", "yaml-metadata", "cloud-storage", "web"], "topics": [], "urls": [], "use_cases": ["find publicly available datasets hosted on AWS S3", "discover open datasets for machine learning research", "list my dataset in the Registry of Open Data on AWS", "browse datasets by provider like NASA, NOAA, or NIH", "find cloud-hosted data to analyze without download costs", "get YAML metadata for all registered open datasets"], "what_it_is": "A registry of publicly available datasets that can be accessed via AWS resources, with each dataset described in a YAML metadata file. It powers the Registry of Open Data on AWS website, letting users discover and share large datasets hosted on S3.", "when_to_avoid": ["you need datasets not accessible via AWS resources", "you want a general-purpose dataset search beyond the AWS ecosystem", "you need guaranteed AWS support or maintenance of the datasets themselves"], "when_to_choose": ["you need to discover large public datasets already hosted on S3", "you want to avoid egress and storage costs by analyzing data in AWS", "you want to publish your own open dataset to a wide audience"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/open-data-registry", "repo": "awslabs/open-data-registry", "role": "main", "score": 77}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.276548+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:25:22.388147+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "25c9f31a31a396d78eb1396ca096ac34b26a13e77bcd5d49f597bf5b34409cc4", "fetched_at": "2026-08-28T04:05:34.276548+00:00", "kind": "readme", "missing": false, "url": "https://github.com/awslabs/open-data-registry"}, {"content_hash": "c82dd1761ab37830a3f70f562a3352fb2ddf4de08b79a60d6e3bf1141b9ee0fd", "fetched_at": "2026-08-29T11:03:59.462707+00:00", "kind": "homepage", "missing": false, "url": "https://registry.opendata.aws"}, {"content_hash": "27efb8a34ee1da240a3ff3ed45d8d485377617c72478f691be2b0eda2d0d9298", "fetched_at": "2026-08-29T11:03:59.477597+00:00", "kind": "site_page", "missing": false, "url": "https://opendata.aws"}, {"content_hash": "bfd1ec77d9275f9826289d58752167b3e32cecede229292b65f2e881a71acb39", "fetched_at": "2026-08-29T11:03:59.480061+00:00", "kind": "site_page", "missing": false, "url": "https://registry.opendata.aws/biohub-esm-atlas"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.276548+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:25:22.388147+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "25c9f31a31a396d78eb1396ca096ac34b26a13e77bcd5d49f597bf5b34409cc4", "fetched_at": "2026-08-28T04:05:34.276548+00:00", "kind": "readme", "missing": false, "url": "https://github.com/awslabs/open-data-registry"}, {"content_hash": "c82dd1761ab37830a3f70f562a3352fb2ddf4de08b79a60d6e3bf1141b9ee0fd", "fetched_at": "2026-08-29T11:03:59.462707+00:00", "kind": "homepage", "missing": false, "url": "https://registry.opendata.aws"}, {"content_hash": "27efb8a34ee1da240a3ff3ed45d8d485377617c72478f691be2b0eda2d0d9298", "fetched_at": "2026-08-29T11:03:59.477597+00:00", "kind": "site_page", "missing": false, "url": "https://opendata.aws"}, {"content_hash": "bfd1ec77d9275f9826289d58752167b3e32cecede229292b65f2e881a71acb39", "fetched_at": "2026-08-29T11:03:59.480061+00:00", "kind": "site_page", "missing": false, "url": "https://registry.opendata.aws/biohub-esm-atlas"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:25:22.388147+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "25c9f31a31a396d78eb1396ca096ac34b26a13e77bcd5d49f597bf5b34409cc4", "fetched_at": "2026-08-28T04:05:34.276548+00:00", "kind": "readme", "missing": false, "url": "https://github.com/awslabs/open-data-registry"}, {"content_hash": "c82dd1761ab37830a3f70f562a3352fb2ddf4de08b79a60d6e3bf1141b9ee0fd", "fetched_at": "2026-08-29T11:03:59.462707+00:00", "kind": "homepage", "missing": false, "url": "https://registry.opendata.aws"}, {"content_hash": "27efb8a34ee1da240a3ff3ed45d8d485377617c72478f691be2b0eda2d0d9298", "fetched_at": "2026-08-29T11:03:59.477597+00:00", "kind": "site_page", "missing": false, "url": "https://opendata.aws"}, {"content_hash": "bfd1ec77d9275f9826289d58752167b3e32cecede229292b65f2e881a71acb39", "fetched_at": "2026-08-29T11:03:59.480061+00:00", "kind": "site_page", "missing": false, "url": "https://registry.opendata.aws/biohub-esm-atlas"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.276548+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.276548+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.276548+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:25:22.388147+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "25c9f31a31a396d78eb1396ca096ac34b26a13e77bcd5d49f597bf5b34409cc4", "fetched_at": "2026-08-28T04:05:34.276548+00:00", "kind": "readme", "missing": false, "url": "https://github.com/awslabs/open-data-registry"}, {"content_hash": "c82dd1761ab37830a3f70f562a3352fb2ddf4de08b79a60d6e3bf1141b9ee0fd", "fetched_at": "2026-08-29T11:03:59.462707+00:00", "kind": "homepage", "missing": false, "url": "https://registry.opendata.aws"}, {"content_hash": "27efb8a34ee1da240a3ff3ed45d8d485377617c72478f691be2b0eda2d0d9298", "fetched_at": "2026-08-29T11:03:59.477597+00:00", "kind": "site_page", "missing": false, "url": "https://opendata.aws"}, {"content_hash": "bfd1ec77d9275f9826289d58752167b3e32cecede229292b65f2e881a71acb39", "fetched_at": "2026-08-29T11:03:59.480061+00:00", "kind": "site_page", "missing": false, "url": "https://registry.opendata.aws/biohub-esm-atlas"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.276548+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.276548+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:25:22.388147+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "25c9f31a31a396d78eb1396ca096ac34b26a13e77bcd5d49f597bf5b34409cc4", "fetched_at": "2026-08-28T04:05:34.276548+00:00", "kind": "readme", "missing": false, "url": "https://github.com/awslabs/open-data-registry"}, {"content_hash": "c82dd1761ab37830a3f70f562a3352fb2ddf4de08b79a60d6e3bf1141b9ee0fd", "fetched_at": "2026-08-29T11:03:59.462707+00:00", "kind": "homepage", "missing": false, "url": "https://registry.opendata.aws"}, {"content_hash": "27efb8a34ee1da240a3ff3ed45d8d485377617c72478f691be2b0eda2d0d9298", "fetched_at": "2026-08-29T11:03:59.477597+00:00", "kind": "site_page", "missing": false, "url": "https://opendata.aws"}, {"content_hash": "bfd1ec77d9275f9826289d58752167b3e32cecede229292b65f2e881a71acb39", "fetched_at": "2026-08-29T11:03:59.480061+00:00", "kind": "site_page", "missing": false, "url": "https://registry.opendata.aws/biohub-esm-atlas"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.276548+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.276548+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.276548+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:25:22.388147+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "25c9f31a31a396d78eb1396ca096ac34b26a13e77bcd5d49f597bf5b34409cc4", "fetched_at": "2026-08-28T04:05:34.276548+00:00", "kind": "readme", "missing": false, "url": "https://github.com/awslabs/open-data-registry"}, {"content_hash": "c82dd1761ab37830a3f70f562a3352fb2ddf4de08b79a60d6e3bf1141b9ee0fd", "fetched_at": "2026-08-29T11:03:59.462707+00:00", "kind": "homepage", "missing": false, "url": "https://registry.opendata.aws"}, {"content_hash": "27efb8a34ee1da240a3ff3ed45d8d485377617c72478f691be2b0eda2d0d9298", "fetched_at": "2026-08-29T11:03:59.477597+00:00", "kind": "site_page", "missing": false, "url": "https://opendata.aws"}, {"content_hash": "bfd1ec77d9275f9826289d58752167b3e32cecede229292b65f2e881a71acb39", "fetched_at": "2026-08-29T11:03:59.480061+00:00", "kind": "site_page", "missing": false, "url": "https://registry.opendata.aws/biohub-esm-atlas"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.276548+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.276548+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:25:22.388147+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "25c9f31a31a396d78eb1396ca096ac34b26a13e77bcd5d49f597bf5b34409cc4", "fetched_at": "2026-08-28T04:05:34.276548+00:00", "kind": "readme", "missing": false, "url": "https://github.com/awslabs/open-data-registry"}, {"content_hash": "c82dd1761ab37830a3f70f562a3352fb2ddf4de08b79a60d6e3bf1141b9ee0fd", "fetched_at": "2026-08-29T11:03:59.462707+00:00", "kind": "homepage", "missing": false, "url": "https://registry.opendata.aws"}, {"content_hash": "27efb8a34ee1da240a3ff3ed45d8d485377617c72478f691be2b0eda2d0d9298", "fetched_at": "2026-08-29T11:03:59.477597+00:00", "kind": "site_page", "missing": false, "url": "https://opendata.aws"}, {"content_hash": "bfd1ec77d9275f9826289d58752167b3e32cecede229292b65f2e881a71acb39", "fetched_at": "2026-08-29T11:03:59.480061+00:00", "kind": "site_page", "missing": false, "url": "https://registry.opendata.aws/biohub-esm-atlas"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:25:22.388147+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "25c9f31a31a396d78eb1396ca096ac34b26a13e77bcd5d49f597bf5b34409cc4", "fetched_at": "2026-08-28T04:05:34.276548+00:00", "kind": "readme", "missing": false, "url": "https://github.com/awslabs/open-data-registry"}, {"content_hash": "c82dd1761ab37830a3f70f562a3352fb2ddf4de08b79a60d6e3bf1141b9ee0fd", "fetched_at": "2026-08-29T11:03:59.462707+00:00", "kind": "homepage", "missing": false, "url": "https://registry.opendata.aws"}, {"content_hash": "27efb8a34ee1da240a3ff3ed45d8d485377617c72478f691be2b0eda2d0d9298", "fetched_at": "2026-08-29T11:03:59.477597+00:00", "kind": "site_page", "missing": false, "url": "https://opendata.aws"}, {"content_hash": "bfd1ec77d9275f9826289d58752167b3e32cecede229292b65f2e881a71acb39", "fetched_at": "2026-08-29T11:03:59.480061+00:00", "kind": "site_page", "missing": false, "url": "https://registry.opendata.aws/biohub-esm-atlas"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:25:22.388147+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "25c9f31a31a396d78eb1396ca096ac34b26a13e77bcd5d49f597bf5b34409cc4", "fetched_at": "2026-08-28T04:05:34.276548+00:00", "kind": "readme", "missing": false, "url": "https://github.com/awslabs/open-data-registry"}, {"content_hash": "c82dd1761ab37830a3f70f562a3352fb2ddf4de08b79a60d6e3bf1141b9ee0fd", "fetched_at": "2026-08-29T11:03:59.462707+00:00", "kind": "homepage", "missing": false, "url": "https://registry.opendata.aws"}, {"content_hash": "27efb8a34ee1da240a3ff3ed45d8d485377617c72478f691be2b0eda2d0d9298", "fetched_at": "2026-08-29T11:03:59.477597+00:00", "kind": "site_page", "missing": false, "url": "https://opendata.aws"}, {"content_hash": "bfd1ec77d9275f9826289d58752167b3e32cecede229292b65f2e881a71acb39", "fetched_at": "2026-08-29T11:03:59.480061+00:00", "kind": "site_page", "missing": false, "url": "https://registry.opendata.aws/biohub-esm-atlas"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:25:22.388147+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "25c9f31a31a396d78eb1396ca096ac34b26a13e77bcd5d49f597bf5b34409cc4", "fetched_at": "2026-08-28T04:05:34.276548+00:00", "kind": "readme", "missing": false, "url": "https://github.com/awslabs/open-data-registry"}, {"content_hash": "c82dd1761ab37830a3f70f562a3352fb2ddf4de08b79a60d6e3bf1141b9ee0fd", "fetched_at": "2026-08-29T11:03:59.462707+00:00", "kind": "homepage", "missing": false, "url": "https://registry.opendata.aws"}, {"content_hash": "27efb8a34ee1da240a3ff3ed45d8d485377617c72478f691be2b0eda2d0d9298", "fetched_at": "2026-08-29T11:03:59.477597+00:00", "kind": "site_page", "missing": false, "url": "https://opendata.aws"}, {"content_hash": "bfd1ec77d9275f9826289d58752167b3e32cecede229292b65f2e881a71acb39", "fetched_at": "2026-08-29T11:03:59.480061+00:00", "kind": "site_page", "missing": false, "url": "https://registry.opendata.aws/biohub-esm-atlas"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3313, "days_push": 7, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 77, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}