macOS Seatbelt sandbox CLI for developers. Protect credentials (SSH, AWS, GPG) from malicious npm packages, supply chain attacks, and untrusted build scripts. Deny-by-default filesystem isolation. Perfect for Claude Code agentic workflows with --dangerously-skip-permissions.

Open-source security tools for AI agents. Find vulnerabilities, fix root causes, prove compliance.

macOS tool that masks API keys during demos, livestreams, and tutorials. Menu Bar App + VS Code Extension + Chrome Extension.

Protect your secrets and stop the breaches!

Governance infrastructure for AI agents. Risk classification, approval gates, and audit logging for autonomous systems.

Browser-native phishing defense suite with 45 real-time detectors covering AiTM proxy, OAuth abuse, credential harvesting, WebSocket exfiltration, canvas phishing, AI-generated lures, and more. MV3 Chrome extension with zero external dependencies.

Pattern-level command filtering for Claude Code. Blocks the dangerous stuff, asks about the risky stuff, lets the normal stuff through.

428 regex patterns for detecting dangerous commands and credential file access. Data layer for HardStop and compatible AI safety tools.

a secret manager helping you protect secrets and credentials in source code and config files

C++ LSASS protection status monitor for credential theft prevention

Manage and secure AI agents by scanning, protecting, benchmarking, and monitoring them with a single unified command-line interface.