{"adoption": {"forks": 1292, "observed_at": "2026-08-28T04:09:09.877283+00:00", "stars": 5108}, "canonical_url": "https://ross.abutalabs.com/products/corpora", "card": {"archived": false, "artifact_type": "dataset", "description": "A collection of small corpuses of interesting data for the creation of bots and similar stuff.", "domain": ["developer-tools", "education"], "enriched": true, "function": ["data-generation", "nlp", "developer-tools"], "health_score": 58, "homepage": null, "language": "JavaScript", "license": null, "license_family": "other", "maturity": "stable", "member_repos": ["dariusk/corpora"], "name": "dariusk/corpora", "platform": ["cross-platform"], "pushed_at": "2026-01-19T09:43:12+00:00", "repo": "dariusk/corpora", "stars": 5108, "tags": ["corpus", "-data", "creative-coding", "bots", "word-lists", "cc0", "prototyping", "natural-language-processing"], "topics": ["language", "words", "bots", "corpus"], "urls": [], "use_cases": ["get a list of common adjectives or nouns for a twitter bot", "find sample word data for a generative art project", "teach a workshop on making bots without scraping data first", "prototype an idea quickly with small curated datasets", "seed a random name or word generator", "find small JSON datasets for creative writing tools"], "what_it_is": "A collection of small, curated JSON corpora (word lists, names, places, and other categorical data) intended for creative coding, bot creation, and rapid prototyping. It is language-neutral static data released under a CC0 license, designed for teaching and quick experiments rather than exhaustive reference data.", "when_to_avoid": ["you need exhaustive dictionaries or complete linguistic databases with metadata", "you need an API with query capabilities rather than static files", "you need large-scale or production-grade datasets"], "when_to_choose": ["you need small, curated word or category lists for prototyping or creative projects", "you want public-domain (CC0) data usable in any language", "you are teaching and need ready-made interesting data for students"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/corpora", "repo": "dariusk/corpora", "role": "main", "score": 61}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:09:09.877283+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:02:09.924756+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5b415c8580a199aebd9b7aa241091ba4e3b0d9afa9378ee1b4e8e775ebae603a", "fetched_at": "2026-08-28T04:09:09.877283+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dariusk/corpora"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:09:09.877283+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:02:09.924756+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5b415c8580a199aebd9b7aa241091ba4e3b0d9afa9378ee1b4e8e775ebae603a", "fetched_at": "2026-08-28T04:09:09.877283+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dariusk/corpora"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:02:09.924756+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5b415c8580a199aebd9b7aa241091ba4e3b0d9afa9378ee1b4e8e775ebae603a", "fetched_at": "2026-08-28T04:09:09.877283+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dariusk/corpora"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:09:09.877283+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:09:09.877283+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:09:09.877283+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:02:09.924756+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5b415c8580a199aebd9b7aa241091ba4e3b0d9afa9378ee1b4e8e775ebae603a", "fetched_at": "2026-08-28T04:09:09.877283+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dariusk/corpora"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:09:09.877283+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:09:09.877283+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:02:09.924756+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5b415c8580a199aebd9b7aa241091ba4e3b0d9afa9378ee1b4e8e775ebae603a", "fetched_at": "2026-08-28T04:09:09.877283+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dariusk/corpora"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:09:09.877283+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:09:09.877283+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:09:09.877283+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:02:09.924756+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5b415c8580a199aebd9b7aa241091ba4e3b0d9afa9378ee1b4e8e775ebae603a", "fetched_at": "2026-08-28T04:09:09.877283+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dariusk/corpora"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:09:09.877283+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:09:09.877283+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:02:09.924756+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5b415c8580a199aebd9b7aa241091ba4e3b0d9afa9378ee1b4e8e775ebae603a", "fetched_at": "2026-08-28T04:09:09.877283+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dariusk/corpora"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:02:09.924756+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5b415c8580a199aebd9b7aa241091ba4e3b0d9afa9378ee1b4e8e775ebae603a", "fetched_at": "2026-08-28T04:09:09.877283+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dariusk/corpora"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:02:09.924756+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5b415c8580a199aebd9b7aa241091ba4e3b0d9afa9378ee1b4e8e775ebae603a", "fetched_at": "2026-08-28T04:09:09.877283+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dariusk/corpora"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:02:09.924756+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5b415c8580a199aebd9b7aa241091ba4e3b0d9afa9378ee1b4e8e775ebae603a", "fetched_at": "2026-08-28T04:09:09.877283+00:00", "kind": "readme", "missing": false, "url": "https://github.com/dariusk/corpora"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 63, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 4575, "days_push": 226, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 61, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}