HOL Guard brings antivirus-style runtime protection to AI agents. It evaluates supported agent actions and local artifacts for secret exposure, prompt injection, unsafe commands, malicious packages, and MCP risks. Guard can allow safe work, block known threats, pause ambiguous ac
How to install hol-guard?
hashgraph-online/hol-guard
$git clone https://github.com/hashgraph-online/hol-guardInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install hol-guard by running `git clone https://github.com/hashgraph-online/hol-guard`, then use it for the current task and follow its documentation at https://github.com/hashgraph-online/hol-guard.
README.md
| 1 | # HOL Guard: Open-Source Antivirus for AI Agents |
| 2 | |
| 3 | [](https://pypi.org/project/hol-guard/) |
| 4 | [](https://pypi.org/project/plugin-scanner/) |
| 5 | [](https://pypi.org/project/hol-guard/) |
| 6 | [](https://pypi.org/project/plugin-scanner/) |
| 7 | [](#install-the-package-you-need) |
| 8 | [](https://github.com/hashgraph-online/hol-guard/actions/workflows/ci.yml) |
| 9 | [](https://github.com/hashgraph-online/hol-guard/actions/workflows/publish.yml) |
| 10 | [](https://github.com/hashgraph-online/hol-guard/pkgs/container/hol-guard) |
| 11 | [](https://scorecard.dev/viewer/?uri=github.com/hashgraph-online/hol-guard) |
| 12 | [](./LICENSE) |
| 13 | [](https://github.com/hashgraph-online/hol-guard/stargazers) |
| 14 | [](https://github.com/astral-sh/ruff) |
| 15 | |
| 16 | |  | **Stop risky AI actions before they compromise your machine.** HOL Guard is a local-first security layer for AI agents, tools, plugins, skills, MCP servers, and package installs.<br><br>[Install HOL Guard](https://hol.org/guard/activate)<br>[Read the documentation](https://github.com/hashgraph-online/hol-guard/blob/main/docs/guard/get-started.md)<br>[PyPI Package (`hol-guard`)](https://pypi.org/project/hol-guard/)<br>[Report an Issue](https://github.com/hashgraph-online/hol-guard/issues) | |
| 17 | | :--- | :--- | |
| 18 | |
| 19 | HOL Guard brings antivirus-style runtime protection to AI agents. It evaluates supported agent actions and local artifacts for secret exposure, prompt injection, unsafe commands, malicious packages, and MCP risks. Guard can allow safe work, block known threats, pause ambiguous actions for approval, and record security receipts for later review. |
| 20 | |
| 21 | Use HOL Guard locally without a cloud account. Connect Guard Cloud when you want synchronized evidence, team policies, fleet visibility, and shared approval workflows. |
| 22 | |
| 23 | ## Install HOL Guard |
| 24 | |
| 25 | ```bash |
| 26 | pipx install hol-guard |
| 27 | hol-guard init |
| 28 | ``` |
| 29 | |
| 30 | `hol-guard init` discovers compatible AI agents, explains each setup change before applying it, and guides you through your first protected action. |
| 31 | |
| 32 | [Install guide](https://github.com/hashgraph-online/hol-guard/blob/main/docs/guard/get-started.md) · [Supported agents](https://github.com/hashgraph-online/hol-guard/blob/main/docs/guard/harness-support.md) · [Local vs. cloud](https://github.com/hashgraph-online/hol-guard/blob/main/docs/guard/local-vs-cloud.md) · [Security policy](https://github.com/hashgraph-online/hol-guard/blob/main/SECURITY.md) |
| 33 | |
| 34 | ## What HOL Guard Protects |
| 35 | |
| 36 | | Threat surface | Guard protection | |
| 37 | | :--- | :--- | |
| 38 | | **Agent tool calls** | Evaluates supported shell, file, MCP, prompt, and tool-result events through native hooks, managed proxies, or reversible launch overlays. | |
| 39 | | **Secrets and credentials** | Detects sensitive file access, credential-shaped output, staged exfiltra |
Related
6 picksType
- mcp-scannerA tool to scan MCP servers and tools for security findingsJul 2026
- agent-scanAgent supply chain security scanner.Jul 2026
- falcon-mcpConnects AI agents with CrowdStrike Falcon for security analysis and automation.Jul 2026
- pythonPlug-and-play auth for Python MCP servers.Aug 2025
- auth0-mcp-serverAuth0 MCP Server: Manage Auth0 applications, APIs, actions, logs, and forms using natural languageJul 2026
- ida-pro-mcpVibe reversing with IDA ProJul 2026
