{"adoption": {"forks": 533, "observed_at": "2026-08-28T04:07:05.469331+00:00", "stars": 2628}, "canonical_url": "https://ross.abutalabs.com/products/scio", "card": {"archived": false, "artifact_type": "framework", "description": "A Scala API for Apache Beam and Google Cloud Dataflow.", "domain": ["big-data", "data-science", "cloud-computing", "microservices"], "enriched": true, "function": ["etl", "streaming", "data-science", "machine-learning", "serialization"], "health_score": 97, "homepage": "https://spotify.github.io/scio", "language": "Scala", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["spotify/scio"], "name": "spotify/scio", "platform": ["jvm", "cloud"], "pushed_at": "2026-08-11T19:43:46+00:00", "repo": "spotify/scio", "stars": 2628, "tags": ["apache-beam", "google-cloud-dataflow", "bigquery", "batch-processing", "scala-api", "data-pipelines", "data-engineering"], "topics": ["scala", "bigquery", "google-cloud", "beam", "dataflow", "batch", "streaming", "data", "ml", "scio"], "urls": [], "use_cases": ["write batch data pipelines in Scala on Apache Beam", "run streaming data processing jobs on Google Cloud Dataflow", "read and write BigQuery tables in a type-safe way", "process Avro, Parquet, and Protobuf data at scale", "integrate pipelines with Pub/Sub, Bigtable, and Cloud Storage", "run machine learning pipelines with TensorFlow IO", "develop and test data pipelines interactively with a Scala REPL"], "what_it_is": "Scio is a Scala API for Apache Beam and Google Cloud Dataflow, inspired by Apache Spark and Scalding. It provides a unified batch and streaming programming model with type-safe integrations for Google Cloud products and various data formats.", "when_to_avoid": ["you prefer Python or Java directly over Scala", "you need a runner or cloud other than Beam-supported ones without extra work", "your pipelines are small enough that a simpler tool suffices"], "when_to_choose": ["your team works in Scala and needs a Spark-like API on Beam", "you run data pipelines on Google Cloud Dataflow", "you need unified batch and streaming processing with strong typing", "you want deep integration with Google Cloud data products like BigQuery"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/scio", "repo": "spotify/scio", "role": "main", "score": 96}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:05.469331+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:19:42.905622+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "01fdd9bf4b4d9567bee3c911d53ec9d8f5731b977f48d2a80be7203ae1f2f530", "fetched_at": "2026-08-28T04:07:05.469331+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spotify/scio"}, {"content_hash": "0d385c672f4ad8762dbf91c9e3dce5bea5c60b3164ffd10b31b2e02497c01137", "fetched_at": "2026-08-29T10:02:31.338185+00:00", "kind": "homepage", "missing": false, "url": "https://spotify.github.io/scio"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:05.469331+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:19:42.905622+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "01fdd9bf4b4d9567bee3c911d53ec9d8f5731b977f48d2a80be7203ae1f2f530", "fetched_at": "2026-08-28T04:07:05.469331+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spotify/scio"}, {"content_hash": "0d385c672f4ad8762dbf91c9e3dce5bea5c60b3164ffd10b31b2e02497c01137", "fetched_at": "2026-08-29T10:02:31.338185+00:00", "kind": "homepage", "missing": false, "url": "https://spotify.github.io/scio"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:19:42.905622+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "01fdd9bf4b4d9567bee3c911d53ec9d8f5731b977f48d2a80be7203ae1f2f530", "fetched_at": "2026-08-28T04:07:05.469331+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spotify/scio"}, {"content_hash": "0d385c672f4ad8762dbf91c9e3dce5bea5c60b3164ffd10b31b2e02497c01137", "fetched_at": "2026-08-29T10:02:31.338185+00:00", "kind": "homepage", "missing": false, "url": "https://spotify.github.io/scio"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:05.469331+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:05.469331+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:05.469331+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:19:42.905622+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "01fdd9bf4b4d9567bee3c911d53ec9d8f5731b977f48d2a80be7203ae1f2f530", "fetched_at": "2026-08-28T04:07:05.469331+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spotify/scio"}, {"content_hash": "0d385c672f4ad8762dbf91c9e3dce5bea5c60b3164ffd10b31b2e02497c01137", "fetched_at": "2026-08-29T10:02:31.338185+00:00", "kind": "homepage", "missing": false, "url": "https://spotify.github.io/scio"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:05.469331+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:05.469331+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:19:42.905622+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "01fdd9bf4b4d9567bee3c911d53ec9d8f5731b977f48d2a80be7203ae1f2f530", "fetched_at": "2026-08-28T04:07:05.469331+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spotify/scio"}, {"content_hash": "0d385c672f4ad8762dbf91c9e3dce5bea5c60b3164ffd10b31b2e02497c01137", "fetched_at": "2026-08-29T10:02:31.338185+00:00", "kind": "homepage", "missing": false, "url": "https://spotify.github.io/scio"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:05.469331+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:05.469331+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:05.469331+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:19:42.905622+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "01fdd9bf4b4d9567bee3c911d53ec9d8f5731b977f48d2a80be7203ae1f2f530", "fetched_at": "2026-08-28T04:07:05.469331+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spotify/scio"}, {"content_hash": "0d385c672f4ad8762dbf91c9e3dce5bea5c60b3164ffd10b31b2e02497c01137", "fetched_at": "2026-08-29T10:02:31.338185+00:00", "kind": "homepage", "missing": false, "url": "https://spotify.github.io/scio"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:05.469331+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:05.469331+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:19:42.905622+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "01fdd9bf4b4d9567bee3c911d53ec9d8f5731b977f48d2a80be7203ae1f2f530", "fetched_at": "2026-08-28T04:07:05.469331+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spotify/scio"}, {"content_hash": "0d385c672f4ad8762dbf91c9e3dce5bea5c60b3164ffd10b31b2e02497c01137", "fetched_at": "2026-08-29T10:02:31.338185+00:00", "kind": "homepage", "missing": false, "url": "https://spotify.github.io/scio"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:19:42.905622+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "01fdd9bf4b4d9567bee3c911d53ec9d8f5731b977f48d2a80be7203ae1f2f530", "fetched_at": "2026-08-28T04:07:05.469331+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spotify/scio"}, {"content_hash": "0d385c672f4ad8762dbf91c9e3dce5bea5c60b3164ffd10b31b2e02497c01137", "fetched_at": "2026-08-29T10:02:31.338185+00:00", "kind": "homepage", "missing": false, "url": "https://spotify.github.io/scio"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:19:42.905622+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "01fdd9bf4b4d9567bee3c911d53ec9d8f5731b977f48d2a80be7203ae1f2f530", "fetched_at": "2026-08-28T04:07:05.469331+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spotify/scio"}, {"content_hash": "0d385c672f4ad8762dbf91c9e3dce5bea5c60b3164ffd10b31b2e02497c01137", "fetched_at": "2026-08-29T10:02:31.338185+00:00", "kind": "homepage", "missing": false, "url": "https://spotify.github.io/scio"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:19:42.905622+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "01fdd9bf4b4d9567bee3c911d53ec9d8f5731b977f48d2a80be7203ae1f2f530", "fetched_at": "2026-08-28T04:07:05.469331+00:00", "kind": "readme", "missing": false, "url": "https://github.com/spotify/scio"}, {"content_hash": "0d385c672f4ad8762dbf91c9e3dce5bea5c60b3164ffd10b31b2e02497c01137", "fetched_at": "2026-08-29T10:02:31.338185+00:00", "kind": "homepage", "missing": false, "url": "https://spotify.github.io/scio"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 97, "longevity": 100, "rhythm": 91}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 4178, "days_push": 22, "days_rel": 63, "gap_med": 20.5, "n_releases_24m": 23}, "score": 96, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}