data-privacy-stack/presidio
Presidio is an open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data, leveraging NLP and customizable pipelines.
Awesome Infra for AI › AI Safety & Guardrails
Tencent/AI-Infra-Guard
AI-Infra-Guard (A.I.G) is an AI red teaming platform developed by Tencent Zhuque Lab, designed to ensure the security of AI models and infrastructure. It offers a suite of tools for self-examination of AI security risks, including OpenClaw Security Scan for identifying vulnerabilities, Agent Scan for analyzing AI agents, MCP Server & Agent Skill Scan, and AI infrastructure vulnerability scanning. A core component is its LLM jailbreak evaluation capability, which assesses the resilience of large language models against adversarial prompts and attempts to bypass safety mechanisms. The platform aims to provide a comprehensive, intelligent, and user-friendly solution for proactively identifying and mitigating security threats across the AI lifecycle, particularly focusing on the inference and operational phases. Recent updates include expanding its fingerprint library for AI web applications, adding new CVE rules, supporting WebSocket agent providers, and enhancing prompt security against direct and indirect injection attacks. AI-Infra-Guard helps organizations secure their AI ecosystems by continuous monitoring and evaluation of AI components and models against known and emerging threats. It primarily targets the operational aspect of AI systems, ensuring they remain robust and secure in production environments.
https://github.com/Tencent/AI-Infra-Guard
Also in AI Safety & Guardrails
NVIDIA-NeMo/Guardrails
NVIDIA NeMo Guardrails is an open-source toolkit for adding programmable guardrails to LLM-based conversational applications, focusing on safety, security, and controlled dialog.
superagent-ai/superagent
Superagent is an open-source SDK providing safety features for AI applications, including prompt injection detection, PII redaction, repository scanning for threats, and red teaming capabilities fo...
microsoft/agent-governance-toolkit
AI Agent Governance Toolkit (AGT) provides policy enforcement, identity management, execution sandboxing, and reliability engineering to secure autonomous AI agents in production.
FailproofAI/failproofai
Observability and policy enforcement for AI agent harnesses, hooking twelve coding and chat harnesses to record every run and block dangerous tool calls before they execute.
protectai/llm-guard
LLM Guard is a comprehensive open-source security toolkit designed to fortify Large Language Model (LLM) interactions by providing robust sanitization, malicious content detection, data leakage pre...
lennney/stop-that-shit
Multi-platform hook and skill guard for AI coding agents that blocks unrequested work such as generated hashes, checksums and task-scope expansion at the harness hook boundary.
kenryu42/cc-safety-net
A PreToolUse hook that blocks destructive commands and secret access before AI coding agents run them, parsing command semantics so shell wrappers and flag reordering cannot bypass it.