{"adoption": {"forks": 1261, "observed_at": "2026-08-28T04:10:43.623080+00:00", "stars": 10644}, "canonical_url": "https://ross.abutalabs.com/products/presidio", "card": {"archived": false, "artifact_type": "library", "description": "An open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. Supports NLP, pattern matching, and customizable pipelines.", "domain": ["privacy", "security", "data-science", "developer-tools"], "enriched": true, "function": ["nlp", "security", "privacy", "ocr", "machine-learning", "sdk"], "health_score": 100, "homepage": "https://presidio.dataprivacystack.org", "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["data-privacy-stack/presidio"], "name": "data-privacy-stack/presidio", "platform": ["python", "cross-platform", "cli"], "pushed_at": "2026-08-26T17:35:40+00:00", "repo": "data-privacy-stack/presidio", "stars": 10644, "tags": ["pii-detection", "data-anonymization", "de-identification", "data-masking", "ner", "spacy", "transformers", "image-redaction", "gdpr-compliance", "phi", "natural-language-processing", "docker", "kubernetes"], "topics": ["python", "pii", "privacy", "data-anonymization", "de-identification", "data-masking", "transformers", "pii-detection", "data-obfuscation", "data-privacy", "data-redaction", "guardrails", "image-redactor", "named-entity-recognition", "nlp", "personally-identifiable-information", "phi", "sensitive-data", "spacy", "anonymization"], "urls": [], "use_cases": ["redact PII from customer support transcripts", "anonymize sensitive data in text before sharing with third parties", "mask credit card numbers and SSNs in logs", "remove personally identifiable information from images", "de-identify PHI in healthcare records", "detect PII in structured/tabular datasets", "build GDPR/CCPA data privacy compliance pipelines"], "what_it_is": "Presidio is an open-source Python SDK for detecting, redacting, masking, and anonymizing sensitive data (PII) in text, images, and structured/semi-structured data. It combines NLP-based named entity recognition, regex, rule-based logic, and checksum validation in customizable pipelines, with modules for analysis, anonymization, image redaction, and structured data.", "when_to_avoid": ["you need a guaranteed complete detection of all sensitive data - automated detection is not exhaustive", "you want a fully managed PII detection service without customization effort", "you need languages or entity types not covered by available recognizers without building custom ones"], "when_to_choose": ["you need customizable, self-hosted PII detection and anonymization in Python", "you want to combine NLP models (spaCy, transformers, stanza) with rule-based recognizers", "you need to redact PII from text, images, and structured data with one toolkit", "you want a library/SDK you can embed in pipelines rather than a managed cloud service"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/presidio", "repo": "data-privacy-stack/presidio", "role": "main", "score": 93}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:10:43.623080+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:18:14.152144+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a7721f700b305ed14074baa20a2a3fb6948074ed9cd01d932063ccd10d5b0a35", "fetched_at": "2026-08-29T08:17:24.833584+00:00", "kind": "homepage", "missing": false, "url": "https://presidio.dataprivacystack.org"}, {"content_hash": "b85e83b7f97c6dc107c28b8697bbdccd6cac24f79d5aba1802c54cb9680be19e", "fetched_at": "2026-08-29T08:17:24.842945+00:00", "kind": "site_page", "missing": false, "url": "https://presidio.dataprivacystack.org/installation"}, {"content_hash": "c1eea7a735be5da96a7da96327295eb23b9771d311862ec3f3928b3c0522f58d", "fetched_at": "2026-08-29T08:17:24.847107+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/presidio/json"}, {"content_hash": "22e9a17f7bda62e5063d329a1b02a9a3787de3364741f7897fd4e9400dbe8784", "fetched_at": "2026-08-29T08:17:24.845138+00:00", "kind": "site_page", "missing": false, "url": "https://presidio.dataprivacystack.org/faq"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:10:43.623080+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:18:14.152144+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a7721f700b305ed14074baa20a2a3fb6948074ed9cd01d932063ccd10d5b0a35", "fetched_at": "2026-08-29T08:17:24.833584+00:00", "kind": "homepage", "missing": false, "url": "https://presidio.dataprivacystack.org"}, {"content_hash": "b85e83b7f97c6dc107c28b8697bbdccd6cac24f79d5aba1802c54cb9680be19e", "fetched_at": "2026-08-29T08:17:24.842945+00:00", "kind": "site_page", "missing": false, "url": "https://presidio.dataprivacystack.org/installation"}, {"content_hash": "c1eea7a735be5da96a7da96327295eb23b9771d311862ec3f3928b3c0522f58d", "fetched_at": "2026-08-29T08:17:24.847107+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/presidio/json"}, {"content_hash": "22e9a17f7bda62e5063d329a1b02a9a3787de3364741f7897fd4e9400dbe8784", "fetched_at": "2026-08-29T08:17:24.845138+00:00", "kind": "site_page", "missing": false, "url": "https://presidio.dataprivacystack.org/faq"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:18:14.152144+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a7721f700b305ed14074baa20a2a3fb6948074ed9cd01d932063ccd10d5b0a35", "fetched_at": "2026-08-29T08:17:24.833584+00:00", "kind": "homepage", "missing": false, "url": "https://presidio.dataprivacystack.org"}, {"content_hash": "b85e83b7f97c6dc107c28b8697bbdccd6cac24f79d5aba1802c54cb9680be19e", "fetched_at": "2026-08-29T08:17:24.842945+00:00", "kind": "site_page", "missing": false, "url": "https://presidio.dataprivacystack.org/installation"}, {"content_hash": "c1eea7a735be5da96a7da96327295eb23b9771d311862ec3f3928b3c0522f58d", "fetched_at": "2026-08-29T08:17:24.847107+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/presidio/json"}, {"content_hash": "22e9a17f7bda62e5063d329a1b02a9a3787de3364741f7897fd4e9400dbe8784", "fetched_at": "2026-08-29T08:17:24.845138+00:00", "kind": "site_page", "missing": false, "url": "https://presidio.dataprivacystack.org/faq"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:10:43.623080+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:10:43.623080+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:10:43.623080+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:18:14.152144+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a7721f700b305ed14074baa20a2a3fb6948074ed9cd01d932063ccd10d5b0a35", "fetched_at": "2026-08-29T08:17:24.833584+00:00", "kind": "homepage", "missing": false, "url": "https://presidio.dataprivacystack.org"}, {"content_hash": "b85e83b7f97c6dc107c28b8697bbdccd6cac24f79d5aba1802c54cb9680be19e", "fetched_at": "2026-08-29T08:17:24.842945+00:00", "kind": "site_page", "missing": false, "url": "https://presidio.dataprivacystack.org/installation"}, {"content_hash": "c1eea7a735be5da96a7da96327295eb23b9771d311862ec3f3928b3c0522f58d", "fetched_at": "2026-08-29T08:17:24.847107+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/presidio/json"}, {"content_hash": "22e9a17f7bda62e5063d329a1b02a9a3787de3364741f7897fd4e9400dbe8784", "fetched_at": "2026-08-29T08:17:24.845138+00:00", "kind": "site_page", "missing": false, "url": "https://presidio.dataprivacystack.org/faq"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:10:43.623080+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:10:43.623080+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:18:14.152144+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a7721f700b305ed14074baa20a2a3fb6948074ed9cd01d932063ccd10d5b0a35", "fetched_at": "2026-08-29T08:17:24.833584+00:00", "kind": "homepage", "missing": false, "url": "https://presidio.dataprivacystack.org"}, {"content_hash": "b85e83b7f97c6dc107c28b8697bbdccd6cac24f79d5aba1802c54cb9680be19e", "fetched_at": "2026-08-29T08:17:24.842945+00:00", "kind": "site_page", "missing": false, "url": "https://presidio.dataprivacystack.org/installation"}, {"content_hash": "c1eea7a735be5da96a7da96327295eb23b9771d311862ec3f3928b3c0522f58d", "fetched_at": "2026-08-29T08:17:24.847107+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/presidio/json"}, {"content_hash": "22e9a17f7bda62e5063d329a1b02a9a3787de3364741f7897fd4e9400dbe8784", "fetched_at": "2026-08-29T08:17:24.845138+00:00", "kind": "site_page", "missing": false, "url": "https://presidio.dataprivacystack.org/faq"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:10:43.623080+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:10:43.623080+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:10:43.623080+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:18:14.152144+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a7721f700b305ed14074baa20a2a3fb6948074ed9cd01d932063ccd10d5b0a35", "fetched_at": "2026-08-29T08:17:24.833584+00:00", "kind": "homepage", "missing": false, "url": "https://presidio.dataprivacystack.org"}, {"content_hash": "b85e83b7f97c6dc107c28b8697bbdccd6cac24f79d5aba1802c54cb9680be19e", "fetched_at": "2026-08-29T08:17:24.842945+00:00", "kind": "site_page", "missing": false, "url": "https://presidio.dataprivacystack.org/installation"}, {"content_hash": "c1eea7a735be5da96a7da96327295eb23b9771d311862ec3f3928b3c0522f58d", "fetched_at": "2026-08-29T08:17:24.847107+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/presidio/json"}, {"content_hash": "22e9a17f7bda62e5063d329a1b02a9a3787de3364741f7897fd4e9400dbe8784", "fetched_at": "2026-08-29T08:17:24.845138+00:00", "kind": "site_page", "missing": false, "url": "https://presidio.dataprivacystack.org/faq"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:10:43.623080+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:10:43.623080+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:18:14.152144+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a7721f700b305ed14074baa20a2a3fb6948074ed9cd01d932063ccd10d5b0a35", "fetched_at": "2026-08-29T08:17:24.833584+00:00", "kind": "homepage", "missing": false, "url": "https://presidio.dataprivacystack.org"}, {"content_hash": "b85e83b7f97c6dc107c28b8697bbdccd6cac24f79d5aba1802c54cb9680be19e", "fetched_at": "2026-08-29T08:17:24.842945+00:00", "kind": "site_page", "missing": false, "url": "https://presidio.dataprivacystack.org/installation"}, {"content_hash": "c1eea7a735be5da96a7da96327295eb23b9771d311862ec3f3928b3c0522f58d", "fetched_at": "2026-08-29T08:17:24.847107+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/presidio/json"}, {"content_hash": "22e9a17f7bda62e5063d329a1b02a9a3787de3364741f7897fd4e9400dbe8784", "fetched_at": "2026-08-29T08:17:24.845138+00:00", "kind": "site_page", "missing": false, "url": "https://presidio.dataprivacystack.org/faq"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:18:14.152144+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a7721f700b305ed14074baa20a2a3fb6948074ed9cd01d932063ccd10d5b0a35", "fetched_at": "2026-08-29T08:17:24.833584+00:00", "kind": "homepage", "missing": false, "url": "https://presidio.dataprivacystack.org"}, {"content_hash": "b85e83b7f97c6dc107c28b8697bbdccd6cac24f79d5aba1802c54cb9680be19e", "fetched_at": "2026-08-29T08:17:24.842945+00:00", "kind": "site_page", "missing": false, "url": "https://presidio.dataprivacystack.org/installation"}, {"content_hash": "c1eea7a735be5da96a7da96327295eb23b9771d311862ec3f3928b3c0522f58d", "fetched_at": "2026-08-29T08:17:24.847107+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/presidio/json"}, {"content_hash": "22e9a17f7bda62e5063d329a1b02a9a3787de3364741f7897fd4e9400dbe8784", "fetched_at": "2026-08-29T08:17:24.845138+00:00", "kind": "site_page", "missing": false, "url": "https://presidio.dataprivacystack.org/faq"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:18:14.152144+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a7721f700b305ed14074baa20a2a3fb6948074ed9cd01d932063ccd10d5b0a35", "fetched_at": "2026-08-29T08:17:24.833584+00:00", "kind": "homepage", "missing": false, "url": "https://presidio.dataprivacystack.org"}, {"content_hash": "b85e83b7f97c6dc107c28b8697bbdccd6cac24f79d5aba1802c54cb9680be19e", "fetched_at": "2026-08-29T08:17:24.842945+00:00", "kind": "site_page", "missing": false, "url": "https://presidio.dataprivacystack.org/installation"}, {"content_hash": "c1eea7a735be5da96a7da96327295eb23b9771d311862ec3f3928b3c0522f58d", "fetched_at": "2026-08-29T08:17:24.847107+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/presidio/json"}, {"content_hash": "22e9a17f7bda62e5063d329a1b02a9a3787de3364741f7897fd4e9400dbe8784", "fetched_at": "2026-08-29T08:17:24.845138+00:00", "kind": "site_page", "missing": false, "url": "https://presidio.dataprivacystack.org/faq"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:18:14.152144+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a7721f700b305ed14074baa20a2a3fb6948074ed9cd01d932063ccd10d5b0a35", "fetched_at": "2026-08-29T08:17:24.833584+00:00", "kind": "homepage", "missing": false, "url": "https://presidio.dataprivacystack.org"}, {"content_hash": "b85e83b7f97c6dc107c28b8697bbdccd6cac24f79d5aba1802c54cb9680be19e", "fetched_at": "2026-08-29T08:17:24.842945+00:00", "kind": "site_page", "missing": false, "url": "https://presidio.dataprivacystack.org/installation"}, {"content_hash": "c1eea7a735be5da96a7da96327295eb23b9771d311862ec3f3928b3c0522f58d", "fetched_at": "2026-08-29T08:17:24.847107+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/presidio/json"}, {"content_hash": "22e9a17f7bda62e5063d329a1b02a9a3787de3364741f7897fd4e9400dbe8784", "fetched_at": "2026-08-29T08:17:24.845138+00:00", "kind": "site_page", "missing": false, "url": "https://presidio.dataprivacystack.org/faq"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 100, "rhythm": 82}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_readme"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3043, "days_push": 7, "days_rel": 42, "gap_med": 60.5, "n_releases_24m": 9}, "score": 93, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}