{"adoption": {"forks": 255, "observed_at": "2026-08-28T04:07:58.550683+00:00", "stars": 3378}, "canonical_url": "https://ross.abutalabs.com/products/distilabel", "card": {"archived": false, "artifact_type": "framework", "description": "Distilabel is a framework for synthetic data and AI feedback for engineers who need fast, reliable and scalable pipelines based on verified research papers.", "domain": ["artificial-intelligence", "large-language-models", "machine-learning"], "enriched": true, "function": ["data-generation", "llm-training", "rag", "machine-learning", "workflow-automation"], "health_score": 91, "homepage": "https://distilabel.argilla.io", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["argilla-io/distilabel"], "name": "argilla-io/distilabel", "platform": ["python", "cross-platform"], "pushed_at": "2026-08-24T22:15:36+00:00", "repo": "argilla-io/distilabel", "stars": 3378, "tags": ["synthetic-data", "ai-feedback", "rlaif", "rlhf", "huggingface", "data-pipelines", "llm-judging", "instruction-datasets", "data-engineering", "natural-language-processing"], "topics": ["ai", "huggingface", "llms", "openai", "python", "rlaif", "rlhf", "synthetic-data", "synthetic-dataset-generation"], "urls": [], "use_cases": ["generate synthetic instruction datasets for llm fine-tuning", "build rlaif pipelines with ai feedback", "create preference datasets for rlhf", "judge and label data with llm-as-a-judge", "generate synthetic training data from research papers", "scale up dataset generation pipelines with huggingface models"], "what_it_is": "Distilabel is a Python framework for building scalable pipelines that generate synthetic data and AI feedback, based on verified research papers. It supports both traditional NLP tasks and LLM scenarios like instruction following, dialogue generation, and LLM-as-a-judge workflows.", "when_to_avoid": ["you need a no-code data labeling UI rather than programmatic pipelines", "your project requires actively maintained upstream support, since original authors have moved on", "you only need simple one-off prompt generation without pipeline orchestration"], "when_to_choose": ["you need reproducible, research-backed synthetic data pipelines", "you want to generate or judge datasets using multiple llm backends", "you are preparing instruction or preference datasets for fine-tuning"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/distilabel", "repo": "argilla-io/distilabel", "role": "main", "score": 74}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:58.550683+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:39:42.149923+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "52410af6e99d7ec7e0ad29ee7101a94ac06bc0a86226d2425fd862726fd5538e", "fetched_at": "2026-08-28T04:07:58.550683+00:00", "kind": "readme", "missing": false, "url": "https://github.com/argilla-io/distilabel"}, {"content_hash": "36c6c3c2e4f9f7e35fb7fea86ea9bfd1cf7fe7061016698b1a017ae1cc7f4a36", "fetched_at": "2026-08-29T09:33:31.703209+00:00", "kind": "homepage", "missing": false, "url": "https://distilabel.argilla.io"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:58.550683+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:39:42.149923+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "52410af6e99d7ec7e0ad29ee7101a94ac06bc0a86226d2425fd862726fd5538e", "fetched_at": "2026-08-28T04:07:58.550683+00:00", "kind": "readme", "missing": false, "url": "https://github.com/argilla-io/distilabel"}, {"content_hash": "36c6c3c2e4f9f7e35fb7fea86ea9bfd1cf7fe7061016698b1a017ae1cc7f4a36", "fetched_at": "2026-08-29T09:33:31.703209+00:00", "kind": "homepage", "missing": false, "url": "https://distilabel.argilla.io"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:39:42.149923+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "52410af6e99d7ec7e0ad29ee7101a94ac06bc0a86226d2425fd862726fd5538e", "fetched_at": "2026-08-28T04:07:58.550683+00:00", "kind": "readme", "missing": false, "url": "https://github.com/argilla-io/distilabel"}, {"content_hash": "36c6c3c2e4f9f7e35fb7fea86ea9bfd1cf7fe7061016698b1a017ae1cc7f4a36", "fetched_at": "2026-08-29T09:33:31.703209+00:00", "kind": "homepage", "missing": false, "url": "https://distilabel.argilla.io"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:58.550683+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:58.550683+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:58.550683+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:39:42.149923+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "52410af6e99d7ec7e0ad29ee7101a94ac06bc0a86226d2425fd862726fd5538e", "fetched_at": "2026-08-28T04:07:58.550683+00:00", "kind": "readme", "missing": false, "url": "https://github.com/argilla-io/distilabel"}, {"content_hash": "36c6c3c2e4f9f7e35fb7fea86ea9bfd1cf7fe7061016698b1a017ae1cc7f4a36", "fetched_at": "2026-08-29T09:33:31.703209+00:00", "kind": "homepage", "missing": false, "url": "https://distilabel.argilla.io"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:58.550683+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:58.550683+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:39:42.149923+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "52410af6e99d7ec7e0ad29ee7101a94ac06bc0a86226d2425fd862726fd5538e", "fetched_at": "2026-08-28T04:07:58.550683+00:00", "kind": "readme", "missing": false, "url": "https://github.com/argilla-io/distilabel"}, {"content_hash": "36c6c3c2e4f9f7e35fb7fea86ea9bfd1cf7fe7061016698b1a017ae1cc7f4a36", "fetched_at": "2026-08-29T09:33:31.703209+00:00", "kind": "homepage", "missing": false, "url": "https://distilabel.argilla.io"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:58.550683+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:58.550683+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:58.550683+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:39:42.149923+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "52410af6e99d7ec7e0ad29ee7101a94ac06bc0a86226d2425fd862726fd5538e", "fetched_at": "2026-08-28T04:07:58.550683+00:00", "kind": "readme", "missing": false, "url": "https://github.com/argilla-io/distilabel"}, {"content_hash": "36c6c3c2e4f9f7e35fb7fea86ea9bfd1cf7fe7061016698b1a017ae1cc7f4a36", "fetched_at": "2026-08-29T09:33:31.703209+00:00", "kind": "homepage", "missing": false, "url": "https://distilabel.argilla.io"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:58.550683+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:58.550683+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:39:42.149923+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "52410af6e99d7ec7e0ad29ee7101a94ac06bc0a86226d2425fd862726fd5538e", "fetched_at": "2026-08-28T04:07:58.550683+00:00", "kind": "readme", "missing": false, "url": "https://github.com/argilla-io/distilabel"}, {"content_hash": "36c6c3c2e4f9f7e35fb7fea86ea9bfd1cf7fe7061016698b1a017ae1cc7f4a36", "fetched_at": "2026-08-29T09:33:31.703209+00:00", "kind": "homepage", "missing": false, "url": "https://distilabel.argilla.io"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:39:42.149923+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "52410af6e99d7ec7e0ad29ee7101a94ac06bc0a86226d2425fd862726fd5538e", "fetched_at": "2026-08-28T04:07:58.550683+00:00", "kind": "readme", "missing": false, "url": "https://github.com/argilla-io/distilabel"}, {"content_hash": "36c6c3c2e4f9f7e35fb7fea86ea9bfd1cf7fe7061016698b1a017ae1cc7f4a36", "fetched_at": "2026-08-29T09:33:31.703209+00:00", "kind": "homepage", "missing": false, "url": "https://distilabel.argilla.io"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:39:42.149923+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "52410af6e99d7ec7e0ad29ee7101a94ac06bc0a86226d2425fd862726fd5538e", "fetched_at": "2026-08-28T04:07:58.550683+00:00", "kind": "readme", "missing": false, "url": "https://github.com/argilla-io/distilabel"}, {"content_hash": "36c6c3c2e4f9f7e35fb7fea86ea9bfd1cf7fe7061016698b1a017ae1cc7f4a36", "fetched_at": "2026-08-29T09:33:31.703209+00:00", "kind": "homepage", "missing": false, "url": "https://distilabel.argilla.io"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:39:42.149923+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "52410af6e99d7ec7e0ad29ee7101a94ac06bc0a86226d2425fd862726fd5538e", "fetched_at": "2026-08-28T04:07:58.550683+00:00", "kind": "readme", "missing": false, "url": "https://github.com/argilla-io/distilabel"}, {"content_hash": "36c6c3c2e4f9f7e35fb7fea86ea9bfd1cf7fe7061016698b1a017ae1cc7f4a36", "fetched_at": "2026-08-29T09:33:31.703209+00:00", "kind": "homepage", "missing": false, "url": "https://distilabel.argilla.io"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 75, "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": 1052, "days_push": 9, "days_rel": 582, "gap_med": 6.0, "n_releases_24m": 7}, "score": 74, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}