# guardrails

Enterprise middleware for securing AI applications against prompt attacks

Prompt Security provides enterprise security middleware that protects AI applications from prompt injection, data leakage, jailbreaks, and toxic content generation. It sits between users and LLM APIs to inspect, filter, and sanitize inputs and outputs in real-time. Supports deployment as a proxy, SDK integration, or browser extension with customizable security policies and compliance reporting.

Behavioral control layer for reliable customer-facing AI agents

Parlant is an open-source framework that adds behavioral governance to conversational AI agents. Instead of relying on prompt engineering alone, it lets teams define explicit policies, conversation guidelines, and behavioral rules that agents follow predictably across multi-turn interactions. Parlant sits between the LLM and the user-facing interface, enforcing consistent agent behavior for customer support, sales, and service automation use cases.

Input and output security scanners for LLM applications

LLM Guard is an open-source security toolkit by Protect AI that provides 15 input scanners and 20 output scanners to protect LLM applications from prompt injection, PII leakage, toxic content, secrets exposure, and data exfiltration. Each scanner is modular and independent — pick the ones you need, configure thresholds, and chain them into a pipeline. The library works with any LLM and has been downloaded over 2.5 million times. MIT licensed, Python 3.9+.

Validate and structure LLM outputs with composable Guards

Guardrails AI is an open-source Python and JavaScript framework for validating and structuring LLM outputs using composable Guards built from a Hub of pre-built validators. It handles structured data extraction with Pydantic models, content safety checks including toxicity, PII detection, competitor mentions, and bias filtering, plus automatic re-prompting when validation fails. The Guardrails Hub offers dozens of validators from regex matching to hallucination detection via LLM judges.

Programmable safety rails for LLM applications

NeMo Guardrails is NVIDIA's open-source toolkit for adding programmable safety rails to LLM applications. It supports five guardrail types — input, dialog, retrieval, execution, and output rails — covering content safety, jailbreak detection, topic control, PII masking, hallucination detection, and fact-checking. The toolkit uses Colang, a domain-specific language for defining conversational constraints, and integrates with OpenAI, Azure, Anthropic, HuggingFace, and LangChain/LangGraph.