by openguardrails · Codex Skill · ★ 338
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
OpenGuardrails-OSS Protect every action your agent takes. OpenGuardrails is an agent-security platform. OpenGuardrails-OSS is its open-source part — a toolkit for giving an AI agent a health-check and an exam. You drive the work through an agent (OpenClaw, Hermes — any autonomous agent) by asking it in natural language; it then uses OpenGuardrails-OSS to audit itself or other agents. It does three things: Scan — a health-check for installed agents, skills, plugins, and MCP servers. Looks for known vulnerabilities, known-malicious components, and dangerous configurations. Think of it as a physical exam. Red-team — a dynamic exam. Runs curated attack prompts from OpenGuardrails Agent Threat Intelligence against a target agent to see whether it falls for them. Think of it as a driving test under hostile conditions. Integrate — ready-to-drop plugin, skill, and SDK so developers can call OpenGuardrails from inside their own agents at runtime. Who is reading this? This project is designed to be driven by an AI agent, not by a human typing commands. Pick the section that matches you: 👤 You are a human — keep reading the For Humans section below. You will not type any commands.
| Stars | 338 |
| Forks | 49 |
| Language | TypeScript |
| Category | Codex Skill |
| Quality Score | 59.068/100 |
| Last Updated | 2026-04-18 |
| Created | 2025-10-22 |
| Platforms | node |
| Est. Tokens | ~680k |
These tools work well together with openguardrails-oss for enhanced workflows:
Looking for a openguardrails-oss alternative? If you're comparing openguardrails-oss with other codex skill tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Universal adapter between AI agents and model providers
Universal adapter between AI agents and model providers
The antivirus for OpenClaw — approve dangerous actions, scan skills, block secret leaks, and keep humans in co
Security plugin for OpenClaw agents - prevents secret leaks, PII exposure, and destructive command execution
A personal 24x7 AI assistant like OpenClaw that runs on your messaging platforms. Send a message on WhatsApp,
Route, manage, and analyze your LLM requests across multiple providers with a unified API interface.
Explore other popular codex skill tools:
openguardrails-oss is Security checkups and red-team tests for AI agents.. It is categorized as a Codex Skill with 338 GitHub stars.
openguardrails-oss is primarily written in TypeScript. It covers topics such as ai-agent-security, ai-gateway, ai-security-gateway.
You can find installation instructions and usage details in the openguardrails-oss GitHub repository at github.com/openguardrails/openguardrails-oss. The project has 338 stars and 49 forks, indicating an active community.
The top alternatives to openguardrails-oss on Agent Skills Hub include thomas, thomas, ClawGuard. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.