{"adoption": {"forks": 63, "observed_at": "2026-09-03T02:15:16.767387+00:00", "stars": 1129}, "canonical_url": "https://ross.abutalabs.com/products/lingua", "card": {"archived": false, "artifact_type": "library", "description": "The most accurate natural language detection library for Rust, suitable for short text and mixed-language text", "domain": ["machine-learning"], "enriched": true, "function": ["nlp", "parser"], "health_score": 98, "homepage": null, "language": "Rust", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["pemistahl/lingua-rs", "pemistahl/lingua-py"], "name": "Lingua", "platform": ["python", "rust", "cross-platform"], "pushed_at": "2026-09-02T20:23:18+00:00", "repo": "pemistahl/lingua-rs", "stars": 1129, "tags": ["language-detection", "language-identification", "offline", "naive-bayes", "short-text", "natural-language-processing"], "topics": ["rust", "rust-library", "rust-crate", "language-detection", "language-classification", "language-recognition", "natural-language-processing", "nlp", "language-identification", "nlp-machine-learning", "language-processing"], "urls": [], "use_cases": ["detect the language of a short text snippet like a tweet", "identify language of single words or phrases", "preprocess text for language-specific NLP pipelines", "route customer emails by language", "detect language in mixed-language text", "run language detection offline without external APIs"], "what_it_is": "Lingua is a language detection library for Python (with a Rust core) that identifies which of 75 languages a text is written in. It is designed for high accuracy on short and mixed-language text, using rule-based and statistical Naive Bayes methods entirely offline.", "when_to_avoid": ["you need neural-network-based detection or embeddings", "you work with Python < 3.12", "you need extremely lightweight detection of only a few major languages"], "when_to_choose": ["you need accurate detection on very short text where CLD3 or langid fail", "you need offline detection without network calls", "you need support for many languages with mixed-language input"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/repos/pemistahl/lingua-rs", "repo": "pemistahl/lingua-rs", "role": "main", "score": 87}, {"path": "/repos/pemistahl/lingua-py", "repo": "pemistahl/lingua-py", "role": "sdk", "score": 84}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-09-03T02:15:16.767387+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:24:08.933600+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "796557c1e6741adbb6d4811a85457261e0a2aeab017bb269eb7f180187fb67c6", "fetched_at": "2026-09-03T02:15:16.767387+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pemistahl/lingua-rs"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-09-03T02:15:16.767387+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:24:08.933600+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "796557c1e6741adbb6d4811a85457261e0a2aeab017bb269eb7f180187fb67c6", "fetched_at": "2026-09-03T02:15:16.767387+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pemistahl/lingua-rs"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:24:08.933600+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "796557c1e6741adbb6d4811a85457261e0a2aeab017bb269eb7f180187fb67c6", "fetched_at": "2026-09-03T02:15:16.767387+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pemistahl/lingua-rs"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-09-03T02:15:16.767387+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-09-03T02:15:16.767387+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-09-03T02:15:16.767387+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:24:08.933600+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "796557c1e6741adbb6d4811a85457261e0a2aeab017bb269eb7f180187fb67c6", "fetched_at": "2026-09-03T02:15:16.767387+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pemistahl/lingua-rs"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-09-03T02:15:16.767387+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-09-03T02:15:16.767387+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:24:08.933600+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "796557c1e6741adbb6d4811a85457261e0a2aeab017bb269eb7f180187fb67c6", "fetched_at": "2026-09-03T02:15:16.767387+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pemistahl/lingua-rs"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-09-03T02:15:16.767387+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-09-03T02:15:16.767387+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-09-03T02:15:16.767387+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:24:08.933600+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "796557c1e6741adbb6d4811a85457261e0a2aeab017bb269eb7f180187fb67c6", "fetched_at": "2026-09-03T02:15:16.767387+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pemistahl/lingua-rs"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-09-03T02:15:16.767387+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-09-03T02:15:16.767387+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:24:08.933600+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "796557c1e6741adbb6d4811a85457261e0a2aeab017bb269eb7f180187fb67c6", "fetched_at": "2026-09-03T02:15:16.767387+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pemistahl/lingua-rs"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:24:08.933600+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "796557c1e6741adbb6d4811a85457261e0a2aeab017bb269eb7f180187fb67c6", "fetched_at": "2026-09-03T02:15:16.767387+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pemistahl/lingua-rs"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:24:08.933600+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "796557c1e6741adbb6d4811a85457261e0a2aeab017bb269eb7f180187fb67c6", "fetched_at": "2026-09-03T02:15:16.767387+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pemistahl/lingua-rs"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:24:08.933600+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "796557c1e6741adbb6d4811a85457261e0a2aeab017bb269eb7f180187fb67c6", "fetched_at": "2026-09-03T02:15:16.767387+00:00", "kind": "readme", "missing": false, "url": "https://github.com/pemistahl/lingua-rs"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 100, "longevity": 100, "rhythm": 62}, "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": 2268, "days_push": 0, "days_rel": 177, "gap_med": 67, "n_releases_24m": 4}, "score": 87, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 3, "stale_scrape": false}}