Back to browse
GitHub Repository

HIPAA-native PHI redaction proxy for AI/LLM interactions. Detects and masks all 18 Safe Harbor identifiers with clinically coherent synthetic replacements.

3 starsPython

Phi-Redactor – HIPAA Phi Redaction Proxy for OpenAI/Anthropic APIs

by dilawargopang·Feb 26, 2026·1 point·1 comment

AI Analysis

●●●BangerSolve My ProblemZero to One

Wire-protocol proxy masks PHI before cloud, restores locally—genuine HIPAA compliance.

Strengths
  • Zero code changes required: only change base_url, not client code
  • Handles multi-turn conversations with encrypted vault preserving redaction mappings
  • All 18 Safe Harbor identifiers detected with spaCy NER, not regex—clinically coherent replacements
Weaknesses
  • Requires Python runtime and spaCy model download; adds localhost overhead per request
  • HIPAA compliance is organizational, not technical—doesn't magically make usage compliant
Category
Target Audience

Healthcare engineers integrating LLMs into HIPAA-compliant workflows.

Similar To

Presidio (Microsoft) · Twixt · cloud-native DLP tools

Similar Projects

Developer Tools●●Solid

LLM Gateway for OpenAI/Anthropic Written in Golang

Runs as a single binary with embedded SQLite and zero-config start, acting as a transparent, provider-agnostic proxy that logs model, tokens, latency, cost and API key hashes while leaving full body capture opt-in. It also proxies streaming responses in real time and exposes stable JSON analytics endpoints — a practical, instrumentable way to get reproducible, audit-ready traces for real LLM traffic, though long-term value depends on how it handles provider edge-cases and SDK compatibility.

Solve My ProblemNiche GemSlick
oatmale
423mo ago