AIGCLIST
HOL Guard
A local policy check for your AI coding agent's riskiest actions — shell, secrets, MCP, and installs
Overview
What it does
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 — install with 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.
Features
- Intercepts agent shell commands before execution
- Checks access to secrets and credential files
- Reviews MCP server connections and tool calls
- Catches package installs before they land
- Allow / block / ask policy, local-first; optional paid Guard Cloud
Install
pipx install hol-guard && hol-guard init
Pricing
Freemium: open-source Apache-2.0 core plus optional paid Guard Cloud (hosted, fully managed).
Reviews (0)
No reviews yet. Be the first to rate this product!
Continue exploring
More in AI Code Assistant
Published tools that share this product's primary category. They are discovery links, not editorial comparisons.
APIDot is a unified AI API platform providing pay-as-you-go access to premium models — GPT Image 2 for image generation and editing, Claude Opus 4.7 and GPT 5.4 for chat, ElevenLabs and MiniMax for music and TTS, and Google Omni Flash for video — all through a single async API with transparent credit pricing and no minimum commitments.
