Use the document. Not the personal data

Name: Use the document. Not the personal data
Availability: InStock
Author: not_wowinter13

by not_wowinter13·Jul 19, 2026·2 points·0 comments

Visit Project View on HN

AI Analysis

●●SolidSolve My ProblemSlick

Format-preserving redaction that handles embedded images better than most PDF tools.

Strengths

•OCR inside embedded images catches PII that simple text extraction misses
•Typed token replacement maintains document readability while anonymizing data
•Luhn checksum validation reduces false positives on credit card detection

Weaknesses

•No mention of on-premise deployment option for highly sensitive compliance needs
•Limited entity types compared to enterprise tools like Microsoft Purview

Similar Projects

Developer Tools●●●Banger

udoc. Dependency-free document extraction in Rust

Pure Rust parsers for legacy Office formats with zero external dependencies.

WizardryBig Brain

newelh

512mo ago

Security●●Solid

HideMyData – macOS PII Removal with Local AI and OCR

Local MLX model redacts PII without sending documents to the cloud.

Solve My ProblemCozy

maciejonos

202mo ago

AI/ML●●Solid

ProofPudding – Document Extraction API with Citations (PDF/Docx)

ProofPudding returns extraction results with explicit links back to the exact page and source text, supports native and scanned PDFs plus DOCX/images, and ships Python/TypeScript SDKs — handy for agents that need auditable facts. It’s a pragmatic product (per-extraction pricing and confidence scores are nice), but the market is crowded; I want clarity on underlying models, real-world accuracy numbers, and how it compares to Document AI/Textract in edge cases.

Solve My ProblemSlick

garai

105mo ago

Productivity●Mid