LLM Guard
MIT-licensed Python toolkit for LLM input/output filtering — prompt-injection detection, PII redaction, toxicity, anonymisation, bias, and more. Top OSS choice for self-hosted runtime guardrails in 2026.
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.