{"adoption": {"forks": 695, "observed_at": "2026-08-28T04:04:46.443508+00:00", "stars": 1452}, "canonical_url": "https://ross.abutalabs.com/products/carbondata", "card": {"archived": false, "artifact_type": "library", "description": "High performance data store solution", "domain": ["big-data", "analytics", "databases"], "enriched": true, "function": ["database", "search-engine", "serialization", "etl"], "health_score": 78, "homepage": "carbondata.apache.org", "language": "Scala", "license": "Apache-2.0", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["apache/carbondata"], "name": "apache/carbondata", "platform": ["jvm", "python", "cloud"], "pushed_at": "2026-08-07T07:07:01+00:00", "repo": "apache/carbondata", "stars": 1452, "tags": ["columnar-format", "apache-spark", "hadoop", "indexed-columnar-store", "data-lake", "agent-metadata", "data-engineering", "docker"], "topics": ["scala", "java", "big-data", "carbondata", "data-format", "apache", "spark", "hadoop"], "urls": [], "use_cases": ["run fast OLAP queries on Spark over HDFS data", "store big data in a compressed indexed columnar format", "accelerate filtered scans to reduce I/O and CPU", "query compressed and encoded data directly", "store metadata for multi-agent AI systems"], "what_it_is": "Apache CarbonData is an indexed columnar data file format and store for fast analytics on big data platforms like Apache Hadoop and Apache Spark. It stores data together with multi-level indexes to accelerate filtered queries, and is also expanding into agent metadata storage for multi-agent systems.", "when_to_avoid": ["you need a widely adopted format with broad ecosystem support like Parquet or ORC", "your stack is not JVM/Spark-based", "you need a general-purpose database rather than a file format"], "when_to_choose": ["you use Spark or Hadoop and need faster analytics than plain Parquet with filter-heavy workloads", "you want a columnar format with built-in indexing and blocklet-level skip scan"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/carbondata", "repo": "apache/carbondata", "role": "main", "score": 75}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:46.443508+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:35:47.398778+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3aeff49727a73f81ea193465997ad17108d34c1314f1d3374729a5adf9c58c65", "fetched_at": "2026-08-28T04:04:46.443508+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/carbondata"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:46.443508+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:35:47.398778+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3aeff49727a73f81ea193465997ad17108d34c1314f1d3374729a5adf9c58c65", "fetched_at": "2026-08-28T04:04:46.443508+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/carbondata"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:35:47.398778+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3aeff49727a73f81ea193465997ad17108d34c1314f1d3374729a5adf9c58c65", "fetched_at": "2026-08-28T04:04:46.443508+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/carbondata"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:46.443508+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:46.443508+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:46.443508+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:35:47.398778+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3aeff49727a73f81ea193465997ad17108d34c1314f1d3374729a5adf9c58c65", "fetched_at": "2026-08-28T04:04:46.443508+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/carbondata"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:46.443508+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:46.443508+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:35:47.398778+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3aeff49727a73f81ea193465997ad17108d34c1314f1d3374729a5adf9c58c65", "fetched_at": "2026-08-28T04:04:46.443508+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/carbondata"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:46.443508+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:46.443508+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:46.443508+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:35:47.398778+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3aeff49727a73f81ea193465997ad17108d34c1314f1d3374729a5adf9c58c65", "fetched_at": "2026-08-28T04:04:46.443508+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/carbondata"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:46.443508+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:46.443508+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:35:47.398778+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3aeff49727a73f81ea193465997ad17108d34c1314f1d3374729a5adf9c58c65", "fetched_at": "2026-08-28T04:04:46.443508+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/carbondata"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:35:47.398778+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3aeff49727a73f81ea193465997ad17108d34c1314f1d3374729a5adf9c58c65", "fetched_at": "2026-08-28T04:04:46.443508+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/carbondata"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:35:47.398778+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3aeff49727a73f81ea193465997ad17108d34c1314f1d3374729a5adf9c58c65", "fetched_at": "2026-08-28T04:04:46.443508+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/carbondata"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:35:47.398778+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3aeff49727a73f81ea193465997ad17108d34c1314f1d3374729a5adf9c58c65", "fetched_at": "2026-08-28T04:04:46.443508+00:00", "kind": "readme", "missing": false, "url": "https://github.com/apache/carbondata"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 96, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3718, "days_push": 26, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 75, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}