OpenGuardrails: A Configurable, Unified, and Scalable Guardrails Platform for Large Language Models

TL;DR

OpenGuardrails tackles safety, jailbreaks, and data leakage in real-world LLM deployments by delivering an open-source, end-to-end guardrails platform. It introduces a unified guard architecture with per-request policy control and probabilistic decision making in logit space, formalized by $p_{\text{unsafe}}$ and $\tau$, enabling continuous calibration across domains. The system combines a quantized 3.3B guard model (derived from a 14B base via GPTQ) with multilingual safety coverage (119 languages) and a new safety dataset collection, achieving strong multilingual benchmarks and production-friendly latency. Its open-source deployment tooling and data resources bridge research and real-world adoption, offering enterprise-grade safety governance with practical efficiency gains and broad applicability across industries.

Abstract

As large language models (LLMs) are increasingly integrated into real-world applications, ensuring their safety, robustness, and privacy compliance has become critical. We present OpenGuardrails, the first fully open-source platform that unifies large-model-based safety detection, manipulation defense, and deployable guardrail infrastructure. OpenGuardrails protects against three major classes of risks: (1) content-safety violations such as harmful or explicit text generation, (2) model-manipulation attacks including prompt injection, jailbreaks, and code-interpreter abuse, and (3) data leakage involving sensitive or private information. Unlike prior modular or rule-based frameworks, OpenGuardrails introduces three core innovations: (1) a Configurable Policy Adaptation mechanism that allows per-request customization of unsafe categories and sensitivity thresholds; (2) a Unified LLM-based Guard Architecture that performs both content-safety and manipulation detection within a single model; and (3) a Quantized, Scalable Model Design that compresses a 14B dense base model to 3.3B via GPTQ while preserving over 98 of benchmark accuracy. The system supports 119 languages, achieves state-of-the-art performance across multilingual safety benchmarks, and can be deployed as a secure gateway or API-based service for enterprise use. All models, datasets, and deployment scripts are released under the Apache 2.0 license.

Figures (1)

• Figure 1: Average F1 scores of OpenGuardrails vs. existing guard models across safety classification benchmarks for Prompts and Responses in English, Chinese, and Multilingual datasets.