{"adoption": {"forks": 169, "observed_at": "2026-09-03T02:15:19.995114+00:00", "stars": 1147}, "canonical_url": "https://ross.abutalabs.com/products/datainfra-redactioneverything", "card": {"archived": false, "artifact_type": "application", "description": "DataInfra Series. Redact EVERYTHING with local llms and vlms.", "domain": ["privacy", "computer-vision", "pdf", "files", "self-hosted", "artificial-intelligence"], "enriched": true, "function": ["ocr", "nlp", "image-processing", "pdf", "privacy", "security", "machine-learning", "llm-inference"], "health_score": 80, "homepage": null, "language": "Python", "license": "NOASSERTION", "license_family": "other", "maturity": "active", "member_repos": ["ttttccxxui/DataInfra-RedactionEverything"], "name": "ttttccxxui/DataInfra-RedactionEverything", "platform": ["python", "self-hosted"], "pushed_at": "2026-09-02T06:11:28+00:00", "repo": "ttttccxxui/DataInfra-RedactionEverything", "stars": 1147, "tags": ["data-redaction", "pii-detection", "document-anonymization", "local-llm", "vlm", "ner", "human-review", "batch-processing", "personal-use-license", "natural-language-processing", "docker", "linux", "gpu"], "topics": [], "urls": [], "use_cases": ["redact pii from pdfs locally", "anonymize scanned documents with ocr", "remove sensitive data from word files and images", "batch redact documents without cloud apis", "detect names ids and signatures in documents", "review and export redacted files", "self-hosted document anonymization"], "what_it_is": "A local-first redaction workbench that detects and anonymizes sensitive information in documents, scanned PDFs, images, Word files, and plain text using local LLMs, VLMs, OCR, and semantic NER. It provides human review, batch processing, configurable industry schemas, and export workflows without sending raw documents to remote APIs.", "when_to_avoid": ["you need a tool for commercial or production use without negotiating a separate license", "you want a lightweight rule-based PII scanner rather than a full workbench with GPU model dependencies", "you cannot run local LLM/VLM models due to limited GPU memory", "you need permissive open-source licensing for redistribution or hosted services"], "when_to_choose": ["you need local-only processing so raw documents never leave your machine", "you need to redact both text and visual elements like seals, faces, and signatures", "you want human-in-the-loop review before finalizing redactions", "you process scanned or image-based documents, not just plain text"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/datainfra-redactioneverything", "repo": "ttttccxxui/DataInfra-RedactionEverything", "role": "main", "score": 60}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-09-03T02:15:19.995114+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:34:13.219799+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "686ba79a9ecd503f52dd844c469bf61499f4c249c2d2436c4634b1f7736971a0", "fetched_at": "2026-09-03T02:15:19.995114+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ttttccxxui/DataInfra-RedactionEverything"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-09-03T02:15:19.995114+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:34:13.219799+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "686ba79a9ecd503f52dd844c469bf61499f4c249c2d2436c4634b1f7736971a0", "fetched_at": "2026-09-03T02:15:19.995114+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ttttccxxui/DataInfra-RedactionEverything"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:34:13.219799+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "686ba79a9ecd503f52dd844c469bf61499f4c249c2d2436c4634b1f7736971a0", "fetched_at": "2026-09-03T02:15:19.995114+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ttttccxxui/DataInfra-RedactionEverything"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-09-03T02:15:19.995114+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-09-03T02:15:19.995114+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-09-03T02:15:19.995114+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:34:13.219799+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "686ba79a9ecd503f52dd844c469bf61499f4c249c2d2436c4634b1f7736971a0", "fetched_at": "2026-09-03T02:15:19.995114+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ttttccxxui/DataInfra-RedactionEverything"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-09-03T02:15:19.995114+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-09-03T02:15:19.995114+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:34:13.219799+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "686ba79a9ecd503f52dd844c469bf61499f4c249c2d2436c4634b1f7736971a0", "fetched_at": "2026-09-03T02:15:19.995114+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ttttccxxui/DataInfra-RedactionEverything"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-09-03T02:15:19.995114+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-09-03T02:15:19.995114+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-09-03T02:15:19.995114+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:34:13.219799+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "686ba79a9ecd503f52dd844c469bf61499f4c249c2d2436c4634b1f7736971a0", "fetched_at": "2026-09-03T02:15:19.995114+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ttttccxxui/DataInfra-RedactionEverything"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-09-03T02:15:19.995114+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-09-03T02:15:19.995114+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:34:13.219799+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "686ba79a9ecd503f52dd844c469bf61499f4c249c2d2436c4634b1f7736971a0", "fetched_at": "2026-09-03T02:15:19.995114+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ttttccxxui/DataInfra-RedactionEverything"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:34:13.219799+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "686ba79a9ecd503f52dd844c469bf61499f4c249c2d2436c4634b1f7736971a0", "fetched_at": "2026-09-03T02:15:19.995114+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ttttccxxui/DataInfra-RedactionEverything"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:34:13.219799+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "686ba79a9ecd503f52dd844c469bf61499f4c249c2d2436c4634b1f7736971a0", "fetched_at": "2026-09-03T02:15:19.995114+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ttttccxxui/DataInfra-RedactionEverything"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:34:13.219799+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "686ba79a9ecd503f52dd844c469bf61499f4c249c2d2436c4634b1f7736971a0", "fetched_at": "2026-09-03T02:15:19.995114+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ttttccxxui/DataInfra-RedactionEverything"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 100, "longevity": 15, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 217, "days_push": 0, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 60, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 3, "stale_scrape": false}}