HOL Guard
HOL Guard is a free, open-source (Apache-2.0), local-first security layer for AI coding agents such as Claude Code, Codex, Cursor and GitHub Copilot CLI. On supported integrations it checks risky shell commands, reads of secret-bearing files, package installs and new or changed MCP tools before they run, lets you allow, ask or block each action, and keeps a local record for review. It installs with pipx (hol-guard) and works offline; optional Guard Cloud adds synced approvals, team policy and dashboards.
Updated
✨ Try AgentScout's free AI image generator →Good for: writing code, coding in the terminal, connecting tools with MCP, agent security and safety, running agents locally
Use cases
About HOL Guard
HOL Guard is listed in our security & governance category and is aimed at builders. HOL Guard is a free, open-source (Apache-2.0), local-first security layer for AI coding agents such as Claude Code, Codex, Cursor and GitHub Copilot CLI. On supported integrations it checks risky shell commands, reads of secret-bearing files, package installs and new or changed MCP tools before they run, lets you allow, ask or block each action, and keeps a local record for review. It installs with pipx (hol-guard) and works offline; optional Guard Cloud adds synced approvals, team policy and dashboards. Pricing, as the maker states it: Free forever for local protection on one machine; Guard Cloud plans: Solo $4.99/mo, Pro $15/mo, Team $30/seat/mo, plus Enterprise. Maturity: Active. We last checked the official link on 2026-10-20.
HOL Guard at a glance
- Category: Security & governance
- Built for: Developers and teams building with AI agents
- Pricing: Free forever for local protection on one machine; Guard Cloud plans: Solo $4.99/mo, Pro $15/mo, Team $30/seat/mo, plus Enterprise (as the maker states it)
- GitHub: hashgraph-online/hol-guard · 959 stars (as of Oct 21, 2026)
- Latest release: v3.52.0, Oct 21, 2026
- Last commit: Oct 21, 2026
- Official site: hol.org/guard
- Listed on AgentScout: Oct 20, 2026
HOL Guard FAQ
What is HOL Guard?
HOL Guard is a free, open-source (Apache-2.0), local-first security layer for AI coding agents such as Claude Code, Codex, Cursor and GitHub Copilot CLI. On supported integrations it checks risky shell commands, reads of secret-bearing files, package installs and new or changed MCP tools before they run, lets you allow, ask or block each action, and keeps a local record for review. It installs with pipx (hol-guard) and works offline; optional Guard Cloud adds synced approvals, team policy and dashboards.
How much does HOL Guard cost?
HOL Guard's pricing, as the maker states it: Free forever for local protection on one machine; Guard Cloud plans: Solo $4.99/mo, Pro $15/mo, Team $30/seat/mo, plus Enterprise. Check the official site for current plans.
Where can I find HOL Guard's source code?
On GitHub at hashgraph-online/hol-guard, which had 959 stars as of Oct 21, 2026. The latest release is v3.52.0 (Oct 21, 2026).
What are alternatives to HOL Guard?
Similar tools include Cisco MCP Scanner, ThinkWatch Lite, Pragor, Wren Pre-sign Check, wren-guard Pro and Is My Agent Safe.
Facts from our link-checked listing, the GitHub repository and the official site. See something wrong? Suggest an edit.
HOL Guard ratings and reviews
Be the first to rate HOL Guard: tap 1 to 5 stars below. A written review is optional.
HOL Guard alternatives
Other security & governance tools in our directory. See all security & governance tools →
Cisco MCP Scanner
Cisco's open-source scanner that checks MCP servers and tools for malicious or risky behaviour using YARA rules and LLM analysis.
ThinkWatch Lite
A local gateway that sits between your coding agents and model providers, letting you switch upstreams, redact secrets before they leave your machine, block dangerous tool calls and see the cost of each request.
Pragor
Coordination and governance layer for teams of people and AI agents, not an autonomous agent: a shared board with tasks, directed messages, approvals, files and an attributable activity record, where agents connect over REST or project MCP access.
Wren Pre-sign Check
Wren Pre-sign Check is a pay-per-call x402 API that an AI agent calls before it signs anything with its wallet. Send a transaction (to + data), an EIP-712 typed-data payload or untrusted text, and it returns block, review or allow, the decoded call in plain words and every finding: unlimited approvals, Permit and Permit2 signatures, setApprovalForAll, EIP-7702 delegation, contract deployment and injected instructions. With an optional wren-guard policy (allowlist, spenders, caps) it also blocks unknown recipients, over-cap amounts and lookalike addresses. It is a static check and stores nothing you send; free demos show real output.
wren-guard Pro
wren-guard Pro is a TypeScript guard library for AI agents that hold or move funds on Base and other EVM chains (viem, CDP AgentKit, Privy, Eliza and similar stacks). It enforces allowlisted, capped and simulated sends, decodes calldata and signatures to flag unlimited approvals, Permit, Permit2, setApprovalForAll and EIP-7702 delegation, screens for injected instructions and watches nonces. It ships with an 89-scenario attack corpus drawn from public agent wallet incidents and a GitHub Action that fails CI if your agent's policy would let a known attack through. The original Python wren-guard is free and MIT licensed.
Is My Agent Safe
Is My Agent Safe checks your OpenClaw version and security audit output in plain English, showing which published security fixes you are missing and which breaking changes lie before the latest release; free check, full report $29 one-off.
Related lists
🏆 Ranked in: MCP servers that work with Cursor · MCP servers that work with Codex
🧭 Task guides: Local and self-hosted tools for terminal coding · Guardrail and policy tools for agent security
Badge for makers
Built HOL Guard? Add this badge to your README or site. It links back to this page. About badges
