Apache-2.0, local-first antivirus for AI coding agents, installed via pipx; protects Codex, Claude Code, Cursor and more — no documented DeepSeek Harness adapter yet.
DSH integration
Ecosystem-related
Author-claimed
Safety audit
Unaudited
Last verified
2026-08-21
License
Apache-2.0
01What can it help you accomplish?
Protect AI coding-agent sessions on the same machine from risky tool calls, secret access and prompt injection
Runtime evaluation of supported shell, file, MCP, prompt, and tool-result events; safe work allowed, known threats blocked, ambiguous actions paused for approval, with security receipts stored locally
Developers running AI coding agents locally who want antivirus-style runtime protection; DeepSeek Harness users should note the README does not yet list a dsh adapter
Review AI supply-chain artifacts — plugins, skills, MCP servers, package installs — before granting trust
Pre-trust reviews plus local receipts and inventory baselines, reviewable from the terminal or the localhost dashboard
Teams that install third-party agent plugins, skills and MCP servers and want a pre-launch review gate
Gate plugin, skill and MCP-server packages with quality and security checks in CI
Quality and security grades with SARIF output via the companion `plugin-scanner` package and the published GitHub Action
Plugin maintainers publishing to agent marketplaces who need a CI quality gate
02How to install into DeepSeek Harness
Prerequisites
- Python 3.10+ (per the README's Python version badge)
- `pipx` for the recommended isolated install
Installation steps
- 01
`pipx install hol-guard`
- 02
`hol-guard init` — discovers compatible AI agents, explains each setup change before applying it, and guides you through your first protected action
Verify the integration
- `command -v hol-guard`
- `hol-guard --version`
Rollback
- `hol-guard uninstall --self` — removes Guard-managed harness wiring, package shims, local Guard state, and uninstalls the current `hol-guard` package
03DSH integration and capability boundaries
Standalone antivirus for AI coding agents installed via pipx; the README lists Codex, Claude Code, Cursor and others as supported agents but does not document a DeepSeek Harness (dsh) adapter
Runtime threat detection for agent actions
supported shell, file, MCP, prompt, and tool-result events from integrated agents→allow / block / pause-for-approval decisions for secrets exposure, prompt injection, unsafe commands, malicious packages and MCP risks
Installs hooks, launcher shims or managed proxies into detected agent configurationsMay pause agent actions pending human approvalApproval center & local dashboard
ambiguous or blocked agent actions→terminal approval queue (`hol-guard approvals`) and a localhost dashboard for reviewing and resolving decisions
Runs a local dashboard at http://localhost:6174Supply-chain scanning
package installs, plugins, skills, MCP servers, hooks and agent configuration→pre-trust reviews, advisory lookups and supply-chain explain traces (`hol-guard supply-chain scan / explain`)
`hol-guard advisories sync` optionally fetches a signed advisory list from advisories.hol.org and requires a Guard Cloud accountplugin-scanner CI quality gate
plugin, skill or marketplace package directories→scored scan / lint / verify / submit results in text, JSON, Markdown or SARIF, usable as a GitHub Actions gate
Separate PyPI package (`plugin-scanner`) must be installed; the GitHub Action can open submission issues when enabled
04Who is it for? When not to use it?
Good for
- Developers running AI coding agents locally who want antivirus-style runtime protection; DeepSeek Harness users should note the README does not yet list a dsh adapter
- Teams that install third-party agent plugins, skills and MCP servers and want a pre-launch review gate
- Plugin maintainers publishing to agent marketplaces who need a CI quality gate
Not for
- The README's supported-agent list (Codex, Claude Code, Copilot CLI, Cursor, Gemini CLI, Hermes, OpenClaw, OpenCode, Antigravity, Kimi Code, Grok, Pi, ZCode) does not include DeepSeek Harness — there is no documented dsh adapter, so Guard cannot be confirmed to protect dsh sessions.
- Enforcement depth varies by agent and event type — Guard prefers the strongest integration each agent exposes, and exact guarantees depend on the upstream support matrix.
- A scan or detection is not a safety guarantee; the README explicitly notes runtime benchmark fixtures are modeled rather than live attacks.
05Compatibility, maintenance and safety notes
- The README's supported-agent list (Codex, Claude Code, Copilot CLI, Cursor, Gemini CLI, Hermes, OpenClaw, OpenCode, Antigravity, Kimi Code, Grok, Pi, ZCode) does not include DeepSeek Harness — there is no documented dsh adapter, so Guard cannot be confirmed to protect dsh sessions.
- Enforcement depth varies by agent and event type — Guard prefers the strongest integration each agent exposes, and exact guarantees depend on the upstream support matrix.
- A scan or detection is not a safety guarantee; the README explicitly notes runtime benchmark fixtures are modeled rather than live attacks.
Apache-2.0 · actively maintained (latest release v2.2.116, 2026-08-20)
06Frequently asked questions
Does HOL Guard protect DeepSeek Harness (dsh) sessions?
Not as documented. The README lists Codex, Claude Code, GitHub Copilot CLI, Cursor, Gemini CLI, Hermes, OpenClaw, OpenCode, Antigravity, Kimi Code, Grok, Pi and ZCode as supported agents — DeepSeek Harness is not among them, though the project says its protection layers are designed to extend as new adapters are added.
How do I install HOL Guard and verify it works?
Run `pipx install hol-guard` followed by `hol-guard init`, which discovers compatible agents on your machine and guides you through your first protected action. Verify the install with `command -v hol-guard` and `hol-guard --version`.
Does it work offline or require a cloud account?
Core protection runs locally without a cloud account. Guard Cloud is optional for synchronized evidence, team policies and shared approvals; advisory database sync requires a Guard Cloud account, and without one Guard keeps using its bundled advisories.
What changes does it make to my machine?
`hol-guard init` installs hooks, launcher shims or managed proxies into detected agent configurations, and each side effect is gated behind an approval checkpoint during setup. `hol-guard uninstall --self` removes the wiring and the package.
What is the difference between hol-guard and plugin-scanner?
`hol-guard` is the end-user antivirus and runtime protection product; `plugin-scanner` is the maintainer/CI companion that lints, verifies and scores plugins, skills and MCP-server packages before release.
07Related DSH workflows
ruflo
by ruvnet
🌊 The original agent meta-harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, RAG integration, and native Claude Code / Codex / Hermes and many more Integrated
reactive-resume
by amruthpillai
A one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!
everos
by evermind-ai
One portable memory layer for every AI agent: local-first, Markdown-native, user-owned, and self-evolving across apps, tools, and workflows.
yao
by yaoapp
✨ All your agents and workspaces in one place, on every device you own. Track tasks on a board, accessible from desktop, mobile, browser, or API. Self-hosted.
08Data and sources
HOL Guard currently integrates with Codex, Claude Code, GitHub Copilot CLI, Cursor, Gemini CLI, Hermes, OpenClaw, OpenCo…
These developer agents are Guard's deepest integrations today, but the product boundary is broader: the same policy, sup…
This page is generated from the project’s public documentation, repository metadata and a structured parse of DSH Plugins; last verified on 2026-08-21. Found an error? Submit a correction.
Best DeepSeek Harness Plugins
Twelve plugins worth installing first — picked from the whole catalog, across every category.