OpenAI Guardrails
OpenAI's official Python/TS library for adding guardrails to Responses API and Assistants API applications. Ships moderation, jailbreak detection, hallucination checks, and PII filters as composable guardrails.
Guardrails AI
Open-source framework for adding input/output validation to LLM applications. Define validators (Pydantic-style) for LLM responses to catch hallucinations, PII leaks, bias, and schema violations. Supports automatic retry and reask on validation failure, with any LLM provider.