mirror of
https://github.com/zenlm/claude-sanitizer.git
synced 2026-11-02 17:24:42 +00:00
- Intelligent context-aware sanitization using Claude API - Two-layer approach: regex pre-screening + AI analysis - Supports both Haiku (cost-effective) and Sonnet (accurate) - Detects API keys, crypto data, PII, financial data - Preserves training value (file paths, function names, errors) - Detailed reporting with severity levels - Smart mode with keyword pre-screening to reduce costs - Cost estimates: ~$0.0043 per 10K entries (Haiku)
7 lines
171 B
Python
7 lines
171 B
Python
"""
|
|
Claude Sanitizer - AI-powered intelligent data sanitization
|
|
Uses Claude to detect and redact sensitive data while preserving training value
|
|
"""
|
|
|
|
__version__ = "0.1.0"
|