{"adoption": {"forks": 579, "observed_at": "2026-08-28T04:09:41.643228+00:00", "stars": 6308}, "canonical_url": "https://ross.abutalabs.com/products/pachyderm", "card": {"archived": false, "artifact_type": "application", "description": "Data-Centric Pipelines and Data Versioning", "domain": ["big-data", "data-science", "machine-learning", "microservices"], "enriched": true, "function": ["etl", "data-science", "workflow-automation", "container-orchestration", "version-control", "streaming"], "health_score": 34, "homepage": "https://www.pachyderm.com/", "language": "Go", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["pachyderm/pachyderm"], "name": "pachyderm/pachyderm", "platform": ["go", "cloud", "self-hosted", "windows"], "pushed_at": "2025-02-03T22:27:18+00:00", "repo": "pachyderm/pachyderm", "stars": 6308, "tags": ["data-versioning", "data-lineage", "data-pipelines", "cicd-for-data", "object-storage", "parallel-processing", "reproducibility", "data-engineering", "containers", "kubernetes", "docker", "linux", "macos"], "topics": ["go", "pachyderm", "docker", "analytics", "big-data", "containers", "distributed-systems", "kubernetes", "data-science", "data-analysis"], "urls": [], "use_cases": ["version large datasets and track lineage across pipeline stages", "build automated data pipelines that trigger on data changes", "run parallelized ETL transformations on Kubernetes", "create reproducible CI/CD workflows for data science and ML", "process multi-stage pipelines across any data type on cloud or on-prem", "deduplicate and store pipeline data in object stores"], "what_it_is": "Pachyderm is a data-centric pipeline platform that automates data transformations with built-in data versioning and lineage tracking. It runs language-agnostic, parallelized multi-stage pipelines on Kubernetes, using standard object stores with deduplication for storage.", "when_to_avoid": ["you only need simple scheduled batch jobs without data versioning", "you cannot operate a Kubernetes cluster or object storage backend", "you want a lightweight single-machine ETL tool", "you need a fully open-source license without commercial terms"], "when_to_choose": ["you need immutable data versioning and lineage for complex multi-stage pipelines", "your team runs data workloads on Kubernetes and wants autoscaling and parallelism", "you want language-agnostic pipeline steps and reproducible data transformations", "you need a CI/CD-style trigger system driven by data changes"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/pachyderm", "repo": "pachyderm/pachyderm", "role": "main", "score": 36}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:09:41.643228+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:46:13.820168+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c1fb19426f11d28852c9f558d115e396040b6c3aa12d68cac3360f8b0b98d715", "fetched_at": "2026-08-28T04:09:41.643228+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pachyderm/pachyderm"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:09:41.643228+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:46:13.820168+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c1fb19426f11d28852c9f558d115e396040b6c3aa12d68cac3360f8b0b98d715", "fetched_at": "2026-08-28T04:09:41.643228+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pachyderm/pachyderm"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:46:13.820168+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c1fb19426f11d28852c9f558d115e396040b6c3aa12d68cac3360f8b0b98d715", "fetched_at": "2026-08-28T04:09:41.643228+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pachyderm/pachyderm"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:09:41.643228+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:09:41.643228+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:09:41.643228+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:46:13.820168+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c1fb19426f11d28852c9f558d115e396040b6c3aa12d68cac3360f8b0b98d715", "fetched_at": "2026-08-28T04:09:41.643228+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pachyderm/pachyderm"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:09:41.643228+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:09:41.643228+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:46:13.820168+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c1fb19426f11d28852c9f558d115e396040b6c3aa12d68cac3360f8b0b98d715", "fetched_at": "2026-08-28T04:09:41.643228+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pachyderm/pachyderm"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:09:41.643228+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:09:41.643228+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:09:41.643228+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:46:13.820168+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c1fb19426f11d28852c9f558d115e396040b6c3aa12d68cac3360f8b0b98d715", "fetched_at": "2026-08-28T04:09:41.643228+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pachyderm/pachyderm"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:09:41.643228+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:09:41.643228+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:46:13.820168+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c1fb19426f11d28852c9f558d115e396040b6c3aa12d68cac3360f8b0b98d715", "fetched_at": "2026-08-28T04:09:41.643228+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pachyderm/pachyderm"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:46:13.820168+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c1fb19426f11d28852c9f558d115e396040b6c3aa12d68cac3360f8b0b98d715", "fetched_at": "2026-08-28T04:09:41.643228+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pachyderm/pachyderm"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:46:13.820168+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c1fb19426f11d28852c9f558d115e396040b6c3aa12d68cac3360f8b0b98d715", "fetched_at": "2026-08-28T04:09:41.643228+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pachyderm/pachyderm"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:46:13.820168+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "c1fb19426f11d28852c9f558d115e396040b6c3aa12d68cac3360f8b0b98d715", "fetched_at": "2026-08-28T04:09:41.643228+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pachyderm/pachyderm"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 4, "longevity": 100, "rhythm": 40}, "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": 4381, "days_push": 576, "days_rel": 595, "gap_med": 19, "n_releases_24m": 6}, "score": 36, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}