// Guard secrets & permissions
NVIDIA-NeMo/Guardrailsv0.24.1
NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
Open source Maintained For agents
IN ONE PARAGRAPH
NVIDIA-NeMo/Guardrails is neMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
Good for: Developers who want their agent (Claude Code, Codex, Cursor…) to guard secrets & permissions.
01How to start
- 1Read the official README for requirements and permissions.
- 2Install it as the official guide describes.
- 3Tell your agent the command exists (e.g. in AGENTS.md / CLAUDE.md) so it knows when to call it.
02Alternatives & comparison
Compare side by side → semgrep Lightweight static analysis for many languages. Find bug variants with patterns that look like source code. ★ 17k garak the LLM vulnerability scanner ★ 9.6k strix Open-source AI penetration testing tool to find and fix your app’s vulnerabilities. ★ 71k trivy Find vulnerabilities, misconfigurations, secrets, SBOM in containers, Kubernetes, code repositories, clouds and more ★ 38k keycloak Open Source Identity and Access Management For Modern Applications and Services ★ 37k
03Related
- ›BlueDot Impact AI Alignment 课程 · BlueDot ImpactEnglish
- ›BlueDot Impact AI Governance 课程 · BlueDot ImpactEnglish
- ›AI Safety, Ethics and Society 教材 · Center for AI Safety / Dan HendrycksEnglish
- ›OWASP Top 10 for LLM Applications · OWASP GenAI Security ProjectMultilingual (incl. EN/ZH)
- ›MITRE ATLAS · MITREEnglish
- All tutorials →