{"adoption": {"forks": 239, "observed_at": "2026-08-28T04:07:09.380120+00:00", "stars": 2670}, "canonical_url": "https://ross.abutalabs.com/products/privacy-filter", "card": {"archived": false, "artifact_type": "library", "description": "OpenAI Privacy Filter", "domain": ["privacy", "machine-learning", "security", "developer-tools"], "enriched": true, "function": ["nlp", "machine-learning", "cli", "privacy", "security"], "health_score": 67, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["openai/privacy-filter"], "name": "openai/privacy-filter", "platform": ["python", "cli", "cross-platform"], "pushed_at": "2026-04-22T19:55:02+00:00", "repo": "openai/privacy-filter", "stars": 2670, "tags": ["pii-detection", "pii-masking", "data-sanitization", "token-classification", "redaction", "on-premises", "fine-tunable", "viterbi-decoding", "natural-language-processing", "gpu", "cpu"], "topics": [], "urls": [], "use_cases": ["redact PII from text files before sharing or training", "sanitize logs and datasets on-premises", "detect names, dates, and other PII in long documents", "fine-tune a PII detector on custom data distributions", "run PII masking locally in a browser or on a laptop", "pipe text through a privacy filter in shell one-liners"], "what_it_is": "OpenAI Privacy Filter is a small bidirectional token-classification model (1.5B total, 50M active parameters) for detecting and masking personally identifiable information in text. The repo provides a Python package and CLI (`opf`) for running one-shot redaction, evaluation, and fine-tuning of the model on-premises.", "when_to_avoid": ["you need structured document (PDF/image) PII redaction rather than plain text", "you require certified compliance guarantees rather than best-effort ML detection", "you need a managed cloud PII API with vendor support", "you lack the hardware to run even a small transformer model"], "when_to_choose": ["you need fast, context-aware PII redaction that runs locally without sending data to external services", "you need a permissively licensed, fine-tunable PII model for commercial deployment", "you process long documents (up to 128k tokens) without chunking", "you want configurable precision/recall tradeoffs for redaction"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/privacy-filter", "repo": "openai/privacy-filter", "role": "main", "score": 49}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:09.380120+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:18:11.293107+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "79c223290f1aa36166969e3ac9cc282aeab333905e0b87aaad1e0c2fed68044e", "fetched_at": "2026-08-28T04:07:09.380120+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/privacy-filter"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:09.380120+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:18:11.293107+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "79c223290f1aa36166969e3ac9cc282aeab333905e0b87aaad1e0c2fed68044e", "fetched_at": "2026-08-28T04:07:09.380120+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/privacy-filter"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:18:11.293107+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "79c223290f1aa36166969e3ac9cc282aeab333905e0b87aaad1e0c2fed68044e", "fetched_at": "2026-08-28T04:07:09.380120+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/privacy-filter"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:09.380120+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:09.380120+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:09.380120+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:18:11.293107+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "79c223290f1aa36166969e3ac9cc282aeab333905e0b87aaad1e0c2fed68044e", "fetched_at": "2026-08-28T04:07:09.380120+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/privacy-filter"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:09.380120+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:09.380120+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:18:11.293107+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "79c223290f1aa36166969e3ac9cc282aeab333905e0b87aaad1e0c2fed68044e", "fetched_at": "2026-08-28T04:07:09.380120+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/privacy-filter"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:09.380120+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:09.380120+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:09.380120+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:18:11.293107+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "79c223290f1aa36166969e3ac9cc282aeab333905e0b87aaad1e0c2fed68044e", "fetched_at": "2026-08-28T04:07:09.380120+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/privacy-filter"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:09.380120+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:09.380120+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:18:11.293107+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "79c223290f1aa36166969e3ac9cc282aeab333905e0b87aaad1e0c2fed68044e", "fetched_at": "2026-08-28T04:07:09.380120+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/privacy-filter"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:18:11.293107+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "79c223290f1aa36166969e3ac9cc282aeab333905e0b87aaad1e0c2fed68044e", "fetched_at": "2026-08-28T04:07:09.380120+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/privacy-filter"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:18:11.293107+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "79c223290f1aa36166969e3ac9cc282aeab333905e0b87aaad1e0c2fed68044e", "fetched_at": "2026-08-28T04:07:09.380120+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/privacy-filter"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:18:11.293107+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "79c223290f1aa36166969e3ac9cc282aeab333905e0b87aaad1e0c2fed68044e", "fetched_at": "2026-08-28T04:07:09.380120+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/privacy-filter"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 78, "longevity": 9, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases", "young"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 138, "days_push": 133, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 49, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}