hol-guard
★ 969
vs
agentic_security
★ 2.0k
hol-guard vs agentic_security
hol-guard: HOL Guard acts as an antivirus for AI harnesses, intercepting tool actions to protect against file changes and network contact. It also includes `plugin-scanner`, a complementary tool for linting and verifying AI plugins and packages in CI environments before release, ensuring quality and security.; agentic_security: Agentic Security is an open-source vulnerability scanner designed to protect AI systems and LLM agent workflows. It detects and mitigates threats like jailbreaks, fuzzing, and multimodal attacks.
01
TL;DR
hol-guardSecurity & Safety · ★ 969
When to choose:
- You run Codex, Claude Code, Copilot CLI, Cursor or similar and want a check before new or changed tools run.
- You maintain plugins, skills or MCP servers and want a CI step such as `plugin-scanner verify .`.
- You want local receipts of what was approved or blocked.
When to skip:
- You need a clear licence in GitHub's metadata today; our data shows none detected.
- You want a minimal tool: the README covers a large surface of commands and integrations.
- You cannot accept extra approval prompts in your agent workflow.
agentic_securitySecurity & Safety · ★ 2.0k
When to choose:
- You want to red-team your own LLM or agent endpoint with multimodal attacks, multi-step jailbreaks, fuzzing and RL-based probes.
- Your target is any HTTP API: you describe it with a plain-text request spec.
- You want a CI check with a budget and a failure threshold, and your own CSV prompt datasets.
When to skip:
- You are not authorised to test the target: only scan systems you own or may test.
- You need to vet MCP servers before installing them: it tests model endpoints, not MCP server code.
- API cost is a problem: scans send many attack prompts.
02
Side-by-Side Comparison
Field
hol-guardagentic_securityCategory
Security & Safety
Security & Safety
Stars
★ 969
★ 2.0k
License
NOASSERTION
Apache-2.0
Install Command
pipx install hol-guard
pip install agentic_security
Updated
1d ago
4d ago
Open Source
Yes
Yes
Tags
AI Security, Plugin Scanner, LLM Guardrail
AI Security, LLM, Vulnerability Scanner
03
Features
hol-guard01Intercepts tool actions and provides an approval center for blocked changes before execution.
02Offers configurable protection levels ranging from Gentle to Paranoid security.
03Scans and verifies AI plugins and packages for security vulnerabilities and quality in CI/CD pipelines.
04Leverages an optional advisory database for comprehensive threat detection and supply chain scanning.
agentic_security01Multimodal Attacks
02Multi-Step Jailbreaks
03Comprehensive Fuzzing
04API Integration & Stress Testing
05RL-Based Attacks
04
Use Cases
hol-guard↳Real-time protection for AI coding assistants and LLM-powered developer tools on local machines.
↳Establishing a CI/CD quality and security gate for AI plugins and marketplace packages before release.
↳Detecting and mitigating AI supply-chain risks, hardcoded secrets, and prompt injections in AI components.
↳Implementing strict security policies for high-security AI development environments and auditing decisions.
agentic_security↳AI system vulnerability testing
↳LLM security research
↳DevSecOps for AI
05
Best For
hol-guardTrendingHidden Gem
agentic_securityTrending
FAQ
FAQ
What is the difference between hol-guard and agentic_security?
Both hol-guard and agentic_security are in the Security & Safety category. hol-guard has 969 stars, while agentic_security has 2.0k stars.
Which is better, hol-guard or agentic_security?
The best choice depends on your use case. Choose hol-guard if Real-time protection for AI coding assistants and LLM-powered developer tools on local machines., and agentic_security if AI system vulnerability testing.
Is hol-guard free or open source?
Yes, hol-guard is open source on GitHub (NOASSERTION).
Is agentic_security free or open source?
Yes, agentic_security is open source on GitHub (Apache-2.0).
Cloud Infrastructure
AdDeploy on DigitalOcean
Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.
→