HOL Guard

Local, open-source policy layer that reviews a coding agent's commands, file reads, package installs and MCP calls before they run — allowing, asking or blocking each action.

Open Source Security
Visit Website ↗ by HOL

What is HOL Guard?

HOL Guard sits between your coding agent and the machine, reviewing each command, file read, package install and MCP call before it runs — and allowing, asking or blocking it.

It is local-first and works with 13 coding agents, with the local Guard free and open source under Apache-2.0.

Key features

  • Allow, ask or block per action — every agent step gets a policy decision before it runs
  • Reviews commands, file reads, package installs and MCP calls, not just shell commands
  • Works with 13 coding agents, including Claude Code, Codex and Cursor
  • Local-first — policy checks run on your own machine
  • Optional Guard Cloud for teams, alongside the free local Guard

Pros

  • Stops unchecked agent actions before they touch files, packages or credentials
  • Local-first — policy checks run on your own machine, not a remote service
  • Works across 13 coding agents with no agent switch required
  • Free local Guard, open source under Apache-2.0

Cons

  • Review prompts add friction by design — every flagged action waits on you
  • Guard Cloud pricing is not published on the official site

HOL Guard at a glance

PricingOpen Source
CategorySecurity
Platformsmac, windows, linux
CompanyHOL
Best forDevelopers running coding agents who want a human checkpoint before an agent touches files, packages or credentials
Official websitehol.org
agent safetypolicy layercoding agentsmcpopen source

How to choose the right Security tool

Security tools protect accounts, devices and data, so the first question is what exactly is being protected — passwords, browsing, files, identity or a whole network — and against which threats. Prefer tools from established vendors with transparent practices: independent audits, clear data policies and a record of fixing vulnerabilities quickly matter more than long feature lists. Check how the tool balances protection with friction; security you disable because it annoys you protects nothing. For password and identity tools, strong encryption and zero-knowledge design are the standards to look for. Finally, remember that no tool replaces basic hygiene — unique passwords, two-factor authentication and regular updates do most of the protective work, and a good tool makes all three easier.

Compare all Security tools →

HOL Guard FAQs

What is HOL Guard?

HOL Guard sits between your coding agent and the machine, reviewing each command, file read, package install and MCP call before it runs — and allowing, asking or blocking it.

What are the main features of HOL Guard?

HOL Guard offers Allow, ask or block per action — every agent step gets a policy decision before it runs, Reviews commands, file reads, package installs and MCP calls, not just shell commands, Works with 13 coding agents, including Claude Code, Codex and Cursor, Local-first — policy checks run on your own machine and Optional Guard Cloud for teams, alongside the free local Guard.

How much does HOL Guard cost?

HOL Guard is open source, so the software itself is free to download, use and self-host. Your only costs are the infrastructure you run it on and any paid services you connect to it.

What are the pros and cons of HOL Guard?

Strengths of HOL Guard include Stops unchecked agent actions before they touch files, packages or credentials; Local-first — policy checks run on your own machine, not a remote service; Works across 13 coding agents with no agent switch required. On the downside, Review prompts add friction by design — every flagged action waits on you; Guard Cloud pricing is not published on the official site.