{"adoption": {"forks": 44, "observed_at": "2026-08-28T04:05:34.231868+00:00", "stars": 1772}, "canonical_url": "https://ross.abutalabs.com/products/budoux", "card": {"archived": false, "artifact_type": "library", "description": null, "domain": ["web-development", "frontend"], "enriched": true, "function": ["nlp", "machine-learning", "parser"], "health_score": 99, "homepage": "https://google.github.io/budoux/", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["google/budoux"], "name": "google/budoux", "platform": ["python", "jvm", "browser", "cross-platform"], "pushed_at": "2026-08-24T00:58:42+00:00", "repo": "google/budoux", "stars": 1772, "tags": ["text-segmentation", "line-breaking", "cjk", "japanese", "chinese", "thai", "typography", "html-processing", "natural-language-processing", "nodejs"], "topics": ["nlp", "machine-learning", "python", "javascript"], "urls": [], "use_cases": ["prevent awkward line breaks in Japanese text on the web", "segment Chinese sentences into phrases", "split Thai text into words without spaces", "add zero-width spaces to HTML for CJK line wrapping", "run lightweight word segmentation client-side without external APIs", "train a custom phrase segmentation model for another language"], "what_it_is": "BudouX is a small, standalone, machine-learning-powered line break organizer that segments sentences into phrases for languages without word boundaries like Japanese, Chinese, and Thai. It ships lightweight pretrained models (~15 KB) with bindings for Python, JavaScript, and Java, and can process HTML input.", "when_to_avoid": ["you need full tokenization or POS tagging rather than phrase-level segmentation", "your language uses spaces between words (e.g. Korean, English)", "you need heavy-duty NLP pipelines with rich linguistic analysis"], "when_to_choose": ["you need CJK/Thai text segmentation with no external dependencies", "bundle size matters, e.g. client-side web typography", "you want pretrained models plus HTML-aware processing"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/budoux", "repo": "google/budoux", "role": "main", "score": 94}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.231868+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:25:57.450910+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e1149fcdcc3837bc0aa128cc5154cb63fb48e250ade26fdf4121fd85d7fe2dc9", "fetched_at": "2026-08-28T04:05:34.231868+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google/budoux"}, {"content_hash": "48710b492fb7a199786d00e79ae42ecc4138d8361915e12c07945203b73b23cd", "fetched_at": "2026-08-29T11:04:07.413298+00:00", "kind": "homepage", "missing": false, "url": "https://google.github.io/budoux/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.231868+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:25:57.450910+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e1149fcdcc3837bc0aa128cc5154cb63fb48e250ade26fdf4121fd85d7fe2dc9", "fetched_at": "2026-08-28T04:05:34.231868+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google/budoux"}, {"content_hash": "48710b492fb7a199786d00e79ae42ecc4138d8361915e12c07945203b73b23cd", "fetched_at": "2026-08-29T11:04:07.413298+00:00", "kind": "homepage", "missing": false, "url": "https://google.github.io/budoux/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:25:57.450910+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e1149fcdcc3837bc0aa128cc5154cb63fb48e250ade26fdf4121fd85d7fe2dc9", "fetched_at": "2026-08-28T04:05:34.231868+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google/budoux"}, {"content_hash": "48710b492fb7a199786d00e79ae42ecc4138d8361915e12c07945203b73b23cd", "fetched_at": "2026-08-29T11:04:07.413298+00:00", "kind": "homepage", "missing": false, "url": "https://google.github.io/budoux/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.231868+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.231868+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.231868+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:25:57.450910+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e1149fcdcc3837bc0aa128cc5154cb63fb48e250ade26fdf4121fd85d7fe2dc9", "fetched_at": "2026-08-28T04:05:34.231868+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google/budoux"}, {"content_hash": "48710b492fb7a199786d00e79ae42ecc4138d8361915e12c07945203b73b23cd", "fetched_at": "2026-08-29T11:04:07.413298+00:00", "kind": "homepage", "missing": false, "url": "https://google.github.io/budoux/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.231868+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.231868+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:25:57.450910+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e1149fcdcc3837bc0aa128cc5154cb63fb48e250ade26fdf4121fd85d7fe2dc9", "fetched_at": "2026-08-28T04:05:34.231868+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google/budoux"}, {"content_hash": "48710b492fb7a199786d00e79ae42ecc4138d8361915e12c07945203b73b23cd", "fetched_at": "2026-08-29T11:04:07.413298+00:00", "kind": "homepage", "missing": false, "url": "https://google.github.io/budoux/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.231868+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.231868+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.231868+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:25:57.450910+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e1149fcdcc3837bc0aa128cc5154cb63fb48e250ade26fdf4121fd85d7fe2dc9", "fetched_at": "2026-08-28T04:05:34.231868+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google/budoux"}, {"content_hash": "48710b492fb7a199786d00e79ae42ecc4138d8361915e12c07945203b73b23cd", "fetched_at": "2026-08-29T11:04:07.413298+00:00", "kind": "homepage", "missing": false, "url": "https://google.github.io/budoux/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.231868+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:34.231868+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:25:57.450910+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e1149fcdcc3837bc0aa128cc5154cb63fb48e250ade26fdf4121fd85d7fe2dc9", "fetched_at": "2026-08-28T04:05:34.231868+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google/budoux"}, {"content_hash": "48710b492fb7a199786d00e79ae42ecc4138d8361915e12c07945203b73b23cd", "fetched_at": "2026-08-29T11:04:07.413298+00:00", "kind": "homepage", "missing": false, "url": "https://google.github.io/budoux/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:25:57.450910+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e1149fcdcc3837bc0aa128cc5154cb63fb48e250ade26fdf4121fd85d7fe2dc9", "fetched_at": "2026-08-28T04:05:34.231868+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google/budoux"}, {"content_hash": "48710b492fb7a199786d00e79ae42ecc4138d8361915e12c07945203b73b23cd", "fetched_at": "2026-08-29T11:04:07.413298+00:00", "kind": "homepage", "missing": false, "url": "https://google.github.io/budoux/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:25:57.450910+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e1149fcdcc3837bc0aa128cc5154cb63fb48e250ade26fdf4121fd85d7fe2dc9", "fetched_at": "2026-08-28T04:05:34.231868+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google/budoux"}, {"content_hash": "48710b492fb7a199786d00e79ae42ecc4138d8361915e12c07945203b73b23cd", "fetched_at": "2026-08-29T11:04:07.413298+00:00", "kind": "homepage", "missing": false, "url": "https://google.github.io/budoux/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:25:57.450910+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e1149fcdcc3837bc0aa128cc5154cb63fb48e250ade26fdf4121fd85d7fe2dc9", "fetched_at": "2026-08-28T04:05:34.231868+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google/budoux"}, {"content_hash": "48710b492fb7a199786d00e79ae42ecc4138d8361915e12c07945203b73b23cd", "fetched_at": "2026-08-29T11:04:07.413298+00:00", "kind": "homepage", "missing": false, "url": "https://google.github.io/budoux/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 100, "rhythm": 84}, "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": 1750, "days_push": 10, "days_rel": 26, "gap_med": 34.5, "n_releases_24m": 9}, "score": 94, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}