Features
Auto-detect over 30 PII types (names, emails, credit cards, API keys, passwords, JWTs, etc.)
Replace sensitive data with placeholders ([[PERSON_1]], [[EMAIL_1]], etc.)
Restore placeholders in AI responses where supported
Browser extension for ChatGPT, Claude, and Gemini (experimental)
HTTP API proxy for apps and SDKs (OpenAI/Anthropic compatible)
ENV file masking for coding agents (Codex, Claude Code, Cursor, Windsurf)
Local-first architecture (no telemetry, cloud-independent)
Self-hostable via Docker (single command)
Live dashboard with request stats (scan time, masked count, model, language)
Mask mode and Route mode (local LLM for sensitive requests)
Open-source and auditable (Apache 2.0 license, GitHub repo)
Cross-platform (macOS, Linux, Windows via Docker)
Keyboard shortcut (⌘⇧K) to mask selected text manually
Data Security Posture Management (DSPM) for hybrid multicloud
Agent Commander for AI agent and copilot security
Context-aware LLM firewalls for prompt and response filtering
Automated data discovery and classification across 1000+ sources
Data minimization automation for cost and risk reduction
Data flow governance and lineage tracking
Data access intelligence and least privilege enforcement
AI governance and compliance with regulations like EU AI Act
Data mapping automation and RoPA report generation
Data subject request (DSR) automation from intake to delivery
Consent management for first- and third-party consent
Breach impact analysis and automated notification
Data curation and sanitization for AI training
Data vectorization and ingestion into vector databases
Unstructured data governance for safe generative AI use
