A set of scanners for prompts and replies: injection, secrets, toxicity, PII. Built by Protect AI.
Others in guardrails
Guardrails AICheck the answer before the customer sees it.
Llama Guard
NeMo GuardrailsRails your application reads from a folder.
Agent Governance ToolkitRules an agent cannot talk its way around.Common questions
Is LLM Guard free to use?
LLM Guard is open source and free to run yourself. You still pay whichever model provider you point it at, and this tutorial is free with no signup.
Do I need to know Python to use LLM Guard?
Basic Python is enough. Functions, dictionaries and imports cover most of what LLM Guard asks of you.
When should I not use LLM Guard?
When something else in guardrails fits the job better. The others in that group are listed below.
Lessons for LLM Guard are being written. Meanwhile the APIs for AI tutorial covers the same ground: state, tools, loops, memory and human approval. Most of it carries straight over.
Start the APIs for AI tutorial →