HOL Guard

Local approvals for AI coding agent actions before they touch your machine

Freemiumhol.orgUpdated 25 Oct 2026

About HOL Guard

HOL Guard is a local-first runtime security layer for AI coding agents such as Claude Code, Codex, Cursor and OpenCode. It runs on your own machine next to the agent and applies a policy at supported agent events. When the agent tries a risky shell command, reads a secret such as a .env file, calls an MCP tool or installs a package, Guard can allow, observe, ask or block the action and keeps a local record of what happened.

Best for

Approving risky agent actions locally, Protecting secrets from coding agents, Reviewing MCP servers, skills and plugins before use
Protecting secrets: Block or ask before an agent reads .env files or credentials.
Reviewing risky commands: Approve destructive shell commands manually while the agent works.
Vetting MCP servers and plugins: Inspect new MCP configuration, skills and plugins before trusting them.
Team policy: Apply shared policy that individual devices cannot weaken.
Plugin CI checks: Run the plugin scanner in GitHub Actions before publishing a plugin.

Not ideal for

Network-level filtering
Users who want a guarantee against prompt injection

Popular with

Software developers
Security engineers
Engineering teams
Plugin and MCP server maintainers

Key features

Pre-action interception
Policy outcomes
Local audit trail
MCP, skills and plugin inspection
Layered policy
Plugin scanner
Risk check
Coverage matrix
Broad agent support

Pros and cons

Pros

Open source under Apache-2.0 with public code and release history
Works offline with no account on the free local tier
Lets you approve or block actions instead of only logging them
Covers MCP servers, skills, plugins and package installs, not just shell commands
Publishes a coverage matrix and states its limits openly

Cons

Coverage depth varies by agent and event type, and some integrations are alpha
Install instructions cover macOS and Linux; Windows support is not stated
Cloud tiers add cost, and annual prices are not listed
Site has no visible terms or company address on the product page

Pricing

Plans as listed by the vendor on 25 Oct 2026. Check their site for current prices.

See hol.org

Free

Local protection on one machine, no account required

Local scanning and command interception
On-device decisions and change diffs
Local policy
Offline support
Local leaked-secret scanning

Solo

$4.99/month

Personal Cloud memory across two devices

2 devices
30-day retention
1 GB storage
Monitoring of up to 5 GitHub repositories
250 credential validity checks per month

Pro

$15/month

Longer history and alerts for one person

5 devices
180-day retention
5 GB storage
Audit log sync
Alert notifications
Policy versioning

Team

$30/user/mo

Shared policy and fleet visibility for teams

Up to 25 devices
365-day retention
25 GB plus 5 GB per seat
Shared policy
Owner queues
Fleet dashboards

Enterprise

Custom/custom

Identity review, evidence export and self-hosted deployment review

Identity and access review
Redacted evidence export via webhook
Volume pricing
Self-hosted or VPC deployment review

Our ratings

Scored out of 10 by the Finder Atlas editorial team.

7.8overall

Action Interception: 8.0
Agent Coverage: 7.8
Ease of Setup: 7.5
Transparency & Openness: 8.6
Pricing Clarity: 7.2

Platforms and integrations

Available on

macOS
Linux
CLI

Works with

Claude Code
Codex
Cursor
OpenCode
GitHub Copilot CLI
GitHub Actions
MCP servers

HOL Guard alternatives

Other tools people compare with HOL Guard.

All 8 alternatives

OpenRouterRated4.5Freemium
One API and one bill for hundreds of AI models across many providers
Compare
OpenAI CodexFreemium
OpenAI's coding agent that writes, reviews and runs code from terminal, IDE, desktop or cloud
Compare
GroqFreemium
Fast, OpenAI-compatible inference API for open models, running on custom LPU chips
Compare
ReplicatePaid
Run, fine-tune and deploy open-source AI models through a pay-per-use API
Compare
LangfuseFreemium
Open-source platform to trace, evaluate and improve LLM applications and agents
Compare

Release history

v3.56.0Oct 24, 2026
Latest release listed on the product page, which highlights per-app protection settings
Latest release listed on the product page, which highlights per-app protection settings.

Reviews

No reviews yet

Used HOL Guard? Help others decide by sharing your experience.

Frequently asked questions

Is HOL Guard free?

The local tool is free and open source under Apache-2.0 and needs no account. Guard Cloud is optional and costs $4.99 (Solo), $15 (Pro) or $30 per seat (Team) per month, with Enterprise on request.

Which AI agents does it support?

The site lists Codex, Claude Code, Cursor, OpenCode, Antigravity CLI, Hermes and OpenClaw, plus GitHub Copilot CLI and several others. Coverage depth differs by agent, so check the public coverage matrix.

Does it work offline?

Yes. Guard Local applies policy and keeps its decision trail on your machine without internet access or a cloud account.

Does it stop all prompt injection?

No. HOL states Guard is not a complete prompt-injection preventer and not a network firewall. It controls supported actions before they run.

How do I install it?

Run pipx install hol-guard and then hol-guard init. The package is published on PyPI and requires Python 3.10 or newer.

Who makes it?

HOL (Hashgraph Online), which publishes the code under the hashgraph-online GitHub organisation. The legal entity listed on hol.org is Hashgraph Online DAO LLC.

More Coding AI tools

View all

Claude

AI Assistants

Anthropic's AI assistant for writing, analysis, coding and working with files

Freemium4.5

Claude Code

Coding AI

Anthropic's coding agent that edits code and runs commands from terminal, IDE or browser

Paid5.0

Cursor