HOL Guard
Local policy checks for AI coding agents before shell, secrets, MCP, and installs run
AI coding agents can run shell commands, read credential files, connect to MCP servers, and install packages on your behalf. HOL Guard is a local-first runtime control layer that intercepts those actions before they run and applies your policy: allow, block, or ask you first. It runs on your own machine alongside the agent, so you keep the decision. The core is open source under Apache-2.0 (pipx install hol-guard && hol-guard init). Teams that want a hosted, fully managed option can add paid Guard Cloud. HOL Guard is not a gateway or network firewall, it does not claim to stop every prompt injection, and a scan is not a safety guarantee. Made by HOL.
