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 loss prevention across email, web, cloud, and devices
Data security posture management for discovery and classification
Insider risk management combining data and behavior signals
AI security: shadow AI discovery, risk assessment, policy enforcement
End-to-end data lineage with context-aware AI classification
Agentic AI detection (Linea) for real-time block and coach
Automated investigation agent (Linea AI Analyst) with reports
Policyless protection with automatic risk detection
Deployment across endpoints, cloud, SaaS, on-prem, and AI tools
Real-time user coaching with contextual prompts
Support for GDPR, SOC 2, GLBA, SEC compliance evidence
Preventing IP theft and trade secret loss in manufacturing
Integration with collaboration tools, code repos, and messaging apps
AI inference risk detection via data lineage
Track data fragments and snippets across modern workflows
