2,002 offers
Free Guardrails & Security — open-source & self-hostable
Safety, validation, and prompt-injection defense
Scores rate free-tier value on a 1–10 scale. How scores work →
-
Microsoft Presidio Guardrails & Security 7.2 An open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. Supports NLP, pattern matching, and customizable pipelines. 9.8k★116/90d31 devs/90d -
NeMo Guardrails Guardrails & Security 7.0 NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems. 6.6k★188/90d19 devs/90d -
PyRIT Guardrails & Security 6.9 The Python Risk Identification Tool for generative AI (PyRIT) is an open source framework built to empower security professionals and engineers to proactively identify risks in generative AI systems. 4k★482/90d17 devs/90d -
Snyk Agent Scan (MCP-Scan) Guardrails & Security 6.2 Security scanner for AI agents, MCP servers and agent skills. 2.7k★212/90d6 devs/90d -
Llama Guard / Purple Llama Guardrails & Security 6.0 Set of tools to assess and improve LLM security. 4.3k★28/90d9 devs/90d -
Agentic Security Guardrails & Security 6.0 Agentic LLM Vulnerability Scanner / AI red teaming kit 🧪 1.9k★66/90d10 devs/90d -
UQLM Guardrails & Security 5.6 UQLM: Uncertainty Quantification for Language Models, is a Python package for UQ-based LLM hallucination detection 1.2k★101/90d5 devs/90d -
spikee Guardrails & Security 4.8 Simple Prompt Injection Kit for Evaluation and Exploitation 216★60/90d5 devs/90d -
Granite Guardian Guardrails & Security 4.1 The Granite Guardian models are designed to detect risks in prompts and responses. 159★9/90d2 devs/90d -
LLM Guard Guardrails & Security 4.0 The Security Toolkit for LLM Interactions 3.1k★0/90d0 devs/90d -
PromptInject Guardrails & Security 3.9 PromptInject is a framework that assembles prompts in a modular fashion to provide a quantitative analysis of the robustness of LLMs to adversarial prompt attacks. 🏆 Best Paper Awards @ NeurIPS ML Safety Workshop 2022 502★0/90d0 devs/90d -
Agent Security Bench Guardrails & Security 3.9 Agent Security Bench (ASB) 266★2/90d1 devs/90d -
ModelScan Guardrails & Security 3.8 Protection against Model Serialization Attacks 728★0/90d0 devs/90d -
promptmap Guardrails & Security 3.6 a security scanner for custom LLM applications 1.2k★0/90d0 devs/90d -
counterfit Guardrails & Security 3.6 a CLI that provides a generic automation layer for assessing the security of ML models 923★0/90d0 devs/90d -
Invariant Guardrails Guardrails & Security 3.5 Guardrails for secure and robust agent development 433★0/90d0 devs/90d -
ai-exploits Guardrails & Security 3.4 A collection of real world AI/ML exploits for responsibly disclosed vulnerabilities 1.7k★0/90d0 devs/90d -
Rebuff Guardrails & Security 3.4 LLM Prompt Injection Detector 1.5k★0/90d0 devs/90d -
Agentic Radar Guardrails & Security 3.4 A security scanner for your LLM agentic workflows 990★0/90d0 devs/90d -
LangKit Guardrails & Security 3.2 🔍 LangKit: An open-source toolkit for monitoring Large Language Models (LLMs). 📚 Extracts signals from prompts & responses, ensuring safety & security. 🛡️ Features include text quality, relevance metrics, & sentiment analysis. 📊 A comprehensive tool for LLM observability. 👀 992★0/90d0 devs/90d -
OpenAI Guardrails (Python) Guardrails & Security 3.2 OpenAI Guardrails - Python 215★0/90d0 devs/90d -
Damn Vulnerable LLM Agent Guardrails & Security 3.1 Intentionally insecure ReAct agent for learning and demonstrating prompt-injection and tool-abuse attacks against agentic apps. 483★0/90d0 devs/90d -
ZenGuard Guardrails & Security 3.1 The fastest Trust Layer for AI Agents 153★0/90d0 devs/90d -
Vigil Guardrails & Security 3.0 ⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs 485★0/90d0 devs/90d -
LLMFuzzer Guardrails & Security 2.9 🧠 LLMFuzzer - Fuzzing Framework for Large Language Models 🧠 LLMFuzzer is the first open-source fuzzing framework specifically designed for Large Language Models (LLMs), especially for their integrations in applications via LLM APIs. 🚀💥 353★0/90d0 devs/90d -
Whistleblower Guardrails & Security 2.8 Whistleblower is a offensive security tool for testing against system prompt leakage and capability discovery of an AI application exposed through API. Built for AI engineers, security researchers and folks who want to know what's going on inside the LLM-based app they use daily 157★0/90d0 devs/90d -
GraySwan Circuit Breakers Guardrails & Security 2.7 Improving Alignment and Robustness with Circuit Breakers 264★0/90d0 devs/90d