A tool for threat modeling AI coding agents by pointing them at a repository to generate an evidence-traced threat model. It supports various architectures and methods for AI security.
HOL Guard is a free, open-source (Apache-2.0) runtime layer for AI coding agents like Claude Code, Codex and Cursor. It watches tool use (shell, secrets, MCP, installs) on your machine instead of trusting the model, and pauses anything risky for your approval. Guard Cloud is optional. pipx install hol-guard && hol-guard init. Scan is not a safety guarantee. Maker: HOL.
GRACE (Graph-RAG Anchored Code Engineering): open Agent Skills for contract-driven AI code generation with semantic markup, knowledge graphs, and support for Claude Code, Codex CLI, and Kilo Code.