Back to browse
GitHub Repository
1 starsPython

Uvx privacy-steward for PII removal in texts

by NeuralNotwork·May 7, 2026·1 point·0 comments

AI Analysis

●●SolidBig BrainSolve My Problem

Native PyTorch port beats the official CLI on speed and batch processing.

Strengths
  • Zero-install execution via uvx simplifies deployment in CI pipelines.
  • Native PyTorch implementation offers faster throughput than the bundled runtime.
  • Typed placeholders allow for granular control over redaction output formats.
Weaknesses
  • Limited to plain-text files, lacking support for structured data like JSON or CSV.
  • Niche appeal restricted to teams specifically needing local-only PII redaction.
Target Audience

Data engineers and privacy compliance officers

Similar To

Microsoft Presidio · Amazon Comprehend

Post Description

Using OpenAI's privacy-filter model behind the scenes. Can run on machines CPUs that are not-so-old (tested on 2020 M1 MacBook Pro).

Similar Projects

Security●●Solid

FunWithText – Free browser PII sanitizer and prompt injection scanner

Runs fully in the browser for regex-based redaction of structured PII (emails, cards, phones, API keys, IPs, SSNs) and offers an optional Claude step to catch names/addresses patterns miss. Clear placeholders like [NAME] and a privacy toggle make it practical for quick, manual workflows, and I like the Norwegian NIN/phone support. It's useful and thoughtfully privacy-first but not novel — the real win would be integrations (batch processing, editor/extension) or independent accuracy metrics for the AI step.

Solve My ProblemSlickNiche Gem
atbj
203mo ago