Pre-execution safety layer for Claude Code - blocks dangerous commands before they run. Part of the Hardstop ecosystem.
Security patterns for detecting dangerous commands and credential file access. Used by HardStop and compatible tools. Part of the Hardstop ecosystem.
Core domain types and Zod schemas for agent-budget-controller
Production-ready HTTP proxy server for AI/LLM governance with OpenAI-compatible API
Core runtime components for AI governance, policy enforcement, budget management, and audit logging