{"adoption": {"forks": 50, "observed_at": "2026-08-28T04:05:55.281419+00:00", "stars": 1923}, "canonical_url": "https://ross.abutalabs.com/products/marginaliasearch", "card": {"archived": false, "artifact_type": "application", "description": "Internet search engine for text-oriented websites. Indexing the small, old and weird web. ", "domain": ["web-development", "crawlers", "self-hosted"], "enriched": true, "function": ["search-engine", "web-scraping", "nlp", "http-server", "self-hosted"], "health_score": 89, "homepage": "https://marginalia-search.com/", "language": "Java", "license": "NOASSERTION", "license_family": "other", "maturity": "active", "member_repos": ["MarginaliaSearch/MarginaliaSearch"], "name": "MarginaliaSearch/MarginaliaSearch", "platform": ["jvm", "self-hosted"], "pushed_at": "2026-08-26T13:09:39+00:00", "repo": "MarginaliaSearch/MarginaliaSearch", "stars": 1923, "tags": ["small-web", "web-crawler", "alt-search", "independent-search-engine", "indexer", "no-cloud", "white-label-search", "search", "natural-language-processing", "linux", "web-server"], "topics": ["search-engine", "no-cloud", "small-web", "internet-search", "indexer", "language-processing", "web-crawler", "alt-search", "self-hostable", "java", "web-scale"], "urls": [], "use_cases": ["search the small, old and weird web for non-commercial content", "self-host my own internet search engine", "run a white-label search engine over my own crawled data", "discover independent blogs and RSS feeds outside big search engines", "crawl and index a custom corpus of websites", "find lost old websites that mainstream engines bury"], "what_it_is": "Marginalia Search is an independent, open-source internet search engine that indexes text-oriented, non-commercial, small and old websites. It includes its own crawler, indexer, and search frontend, and can be self-hosted or run as a white-label search engine over your own crawled or side-loaded data.", "when_to_avoid": ["you need a turnkey search widget for a small site or app docs (use lighter search libraries instead)", "you lack substantial RAM and storage; production-like deployments need ~32GB+ RAM and enterprise SSDs", "you need highly configurable ranking out of the box; configurability is still limited", "you need AI-powered or natural-language question answering"], "when_to_choose": ["you want an independent, privacy-respecting search engine that prioritizes non-commercial content", "you need a self-hostable full search stack (crawler, index, frontend) without cloud dependencies", "you want to search or index text-heavy, hobbyist, or old-web content", "you want traditional information-retrieval search rather than AI/natural-language answers"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/marginaliasearch", "repo": "MarginaliaSearch/MarginaliaSearch", "role": "main", "score": 65}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:55.281419+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:09:37.149188+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "67382306879da8c8d53792c224791985407b7738329f5c0638524cc5dfb6b0cd", "fetched_at": "2026-08-28T04:05:55.281419+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MarginaliaSearch/MarginaliaSearch"}, {"content_hash": "7335942122724cb77451209117c3884ab38737b7eb21c14507957f328bfc503b", "fetched_at": "2026-08-29T10:48:55.801746+00:00", "kind": "homepage", "missing": false, "url": "https://marginalia-search.com/"}, {"content_hash": "53a632f33ebd5e9e6a927b56fcba8a0c3e20ea0d04596d1e6b97e9832e138868", "fetched_at": "2026-08-29T10:48:55.810589+00:00", "kind": "site_page", "missing": false, "url": "https://about.marginalia-search.com/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:55.281419+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:09:37.149188+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "67382306879da8c8d53792c224791985407b7738329f5c0638524cc5dfb6b0cd", "fetched_at": "2026-08-28T04:05:55.281419+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MarginaliaSearch/MarginaliaSearch"}, {"content_hash": "7335942122724cb77451209117c3884ab38737b7eb21c14507957f328bfc503b", "fetched_at": "2026-08-29T10:48:55.801746+00:00", "kind": "homepage", "missing": false, "url": "https://marginalia-search.com/"}, {"content_hash": "53a632f33ebd5e9e6a927b56fcba8a0c3e20ea0d04596d1e6b97e9832e138868", "fetched_at": "2026-08-29T10:48:55.810589+00:00", "kind": "site_page", "missing": false, "url": "https://about.marginalia-search.com/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:09:37.149188+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "67382306879da8c8d53792c224791985407b7738329f5c0638524cc5dfb6b0cd", "fetched_at": "2026-08-28T04:05:55.281419+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MarginaliaSearch/MarginaliaSearch"}, {"content_hash": "7335942122724cb77451209117c3884ab38737b7eb21c14507957f328bfc503b", "fetched_at": "2026-08-29T10:48:55.801746+00:00", "kind": "homepage", "missing": false, "url": "https://marginalia-search.com/"}, {"content_hash": "53a632f33ebd5e9e6a927b56fcba8a0c3e20ea0d04596d1e6b97e9832e138868", "fetched_at": "2026-08-29T10:48:55.810589+00:00", "kind": "site_page", "missing": false, "url": "https://about.marginalia-search.com/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:55.281419+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:55.281419+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:55.281419+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:09:37.149188+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "67382306879da8c8d53792c224791985407b7738329f5c0638524cc5dfb6b0cd", "fetched_at": "2026-08-28T04:05:55.281419+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MarginaliaSearch/MarginaliaSearch"}, {"content_hash": "7335942122724cb77451209117c3884ab38737b7eb21c14507957f328bfc503b", "fetched_at": "2026-08-29T10:48:55.801746+00:00", "kind": "homepage", "missing": false, "url": "https://marginalia-search.com/"}, {"content_hash": "53a632f33ebd5e9e6a927b56fcba8a0c3e20ea0d04596d1e6b97e9832e138868", "fetched_at": "2026-08-29T10:48:55.810589+00:00", "kind": "site_page", "missing": false, "url": "https://about.marginalia-search.com/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:55.281419+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:55.281419+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:09:37.149188+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "67382306879da8c8d53792c224791985407b7738329f5c0638524cc5dfb6b0cd", "fetched_at": "2026-08-28T04:05:55.281419+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MarginaliaSearch/MarginaliaSearch"}, {"content_hash": "7335942122724cb77451209117c3884ab38737b7eb21c14507957f328bfc503b", "fetched_at": "2026-08-29T10:48:55.801746+00:00", "kind": "homepage", "missing": false, "url": "https://marginalia-search.com/"}, {"content_hash": "53a632f33ebd5e9e6a927b56fcba8a0c3e20ea0d04596d1e6b97e9832e138868", "fetched_at": "2026-08-29T10:48:55.810589+00:00", "kind": "site_page", "missing": false, "url": "https://about.marginalia-search.com/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:55.281419+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:55.281419+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:55.281419+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:09:37.149188+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "67382306879da8c8d53792c224791985407b7738329f5c0638524cc5dfb6b0cd", "fetched_at": "2026-08-28T04:05:55.281419+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MarginaliaSearch/MarginaliaSearch"}, {"content_hash": "7335942122724cb77451209117c3884ab38737b7eb21c14507957f328bfc503b", "fetched_at": "2026-08-29T10:48:55.801746+00:00", "kind": "homepage", "missing": false, "url": "https://marginalia-search.com/"}, {"content_hash": "53a632f33ebd5e9e6a927b56fcba8a0c3e20ea0d04596d1e6b97e9832e138868", "fetched_at": "2026-08-29T10:48:55.810589+00:00", "kind": "site_page", "missing": false, "url": "https://about.marginalia-search.com/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:55.281419+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:55.281419+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:09:37.149188+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "67382306879da8c8d53792c224791985407b7738329f5c0638524cc5dfb6b0cd", "fetched_at": "2026-08-28T04:05:55.281419+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MarginaliaSearch/MarginaliaSearch"}, {"content_hash": "7335942122724cb77451209117c3884ab38737b7eb21c14507957f328bfc503b", "fetched_at": "2026-08-29T10:48:55.801746+00:00", "kind": "homepage", "missing": false, "url": "https://marginalia-search.com/"}, {"content_hash": "53a632f33ebd5e9e6a927b56fcba8a0c3e20ea0d04596d1e6b97e9832e138868", "fetched_at": "2026-08-29T10:48:55.810589+00:00", "kind": "site_page", "missing": false, "url": "https://about.marginalia-search.com/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:09:37.149188+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "67382306879da8c8d53792c224791985407b7738329f5c0638524cc5dfb6b0cd", "fetched_at": "2026-08-28T04:05:55.281419+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MarginaliaSearch/MarginaliaSearch"}, {"content_hash": "7335942122724cb77451209117c3884ab38737b7eb21c14507957f328bfc503b", "fetched_at": "2026-08-29T10:48:55.801746+00:00", "kind": "homepage", "missing": false, "url": "https://marginalia-search.com/"}, {"content_hash": "53a632f33ebd5e9e6a927b56fcba8a0c3e20ea0d04596d1e6b97e9832e138868", "fetched_at": "2026-08-29T10:48:55.810589+00:00", "kind": "site_page", "missing": false, "url": "https://about.marginalia-search.com/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:09:37.149188+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "67382306879da8c8d53792c224791985407b7738329f5c0638524cc5dfb6b0cd", "fetched_at": "2026-08-28T04:05:55.281419+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MarginaliaSearch/MarginaliaSearch"}, {"content_hash": "7335942122724cb77451209117c3884ab38737b7eb21c14507957f328bfc503b", "fetched_at": "2026-08-29T10:48:55.801746+00:00", "kind": "homepage", "missing": false, "url": "https://marginalia-search.com/"}, {"content_hash": "53a632f33ebd5e9e6a927b56fcba8a0c3e20ea0d04596d1e6b97e9832e138868", "fetched_at": "2026-08-29T10:48:55.810589+00:00", "kind": "site_page", "missing": false, "url": "https://about.marginalia-search.com/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:09:37.149188+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "67382306879da8c8d53792c224791985407b7738329f5c0638524cc5dfb6b0cd", "fetched_at": "2026-08-28T04:05:55.281419+00:00", "kind": "readme", "missing": false, "url": "https://github.com/MarginaliaSearch/MarginaliaSearch"}, {"content_hash": "7335942122724cb77451209117c3884ab38737b7eb21c14507957f328bfc503b", "fetched_at": "2026-08-29T10:48:55.801746+00:00", "kind": "homepage", "missing": false, "url": "https://marginalia-search.com/"}, {"content_hash": "53a632f33ebd5e9e6a927b56fcba8a0c3e20ea0d04596d1e6b97e9832e138868", "fetched_at": "2026-08-29T10:48:55.810589+00:00", "kind": "site_page", "missing": false, "url": "https://about.marginalia-search.com/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 90, "rhythm": 8}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1262, "days_push": 7, "days_rel": 688, "gap_med": null, "n_releases_24m": 1}, "score": 65, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}