Home › Directory › Security & Guardrails
Security & Guardrails
Guardrails, red-teaming and safety tools for AI systems.
JSON: /api/v1/directory.json (filter on category=security-guardrails)
NVIDIA NeMo Guardrails
Toolkit for adding programmable guardrails to LLM apps.
FreeNo authGuardrails AI
Validators and structured output guardrails for LLMs.
Free tierNo authLlama Guard
Meta's safety classifier models and Purple Llama tools.
FreeNo authLLM Guard
Toolkit for sanitizing and securing LLM interactions.
FreeNo authLakera Guard
Real-time protection against prompt injection and data leaks.
Free tierAPI keyRebuff
Prompt injection detector.
FreeNo authGarak
LLM vulnerability scanner.
FreeNo authPyRIT
Microsoft's risk identification toolkit for generative AI.
FreeNo authOWASP Top 10 for LLM Applications
Top security risks for LLM apps.
FreeNo authMITRE ATLAS
Knowledge base of adversary tactics against AI systems.
FreeNo authNIST AI Risk Management Framework
US framework for managing AI risks.
FreeNo authMicrosoft Presidio
PII detection and anonymization SDK.
FreeNo authOpenAI Moderation API
Free content moderation endpoint.
FreeAPI keyPerspective API
Toxicity scoring API.
FreeAPI keyAzure AI Content Safety
Detect harmful content and prompt attacks.
Free tierAPI keyAmazon Bedrock Guardrails
Configurable safeguards for generative AI apps.
PaidOAuthProtect AI
AI security platform.
PaidAPI keyHiddenLayer
Security for ML models and agents.
PaidAPI keyPrompt Security
Security for GenAI use.
PaidAPI keyInvariant Labs
Agent security and guardrails.
Free tierAPI keyCalypsoAI
Inference-layer security for AI.
PaidAPI key