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
pegasi-ai/reins
Reins is a security framework designed to provide granular control and safety for AI agents, particularly those using tools and interacting with external environments. Its core functionality revolves around enforcing deterministic security policies on every agent action, effectively acting as guardrails to prevent unintended or malicious behaviors. The platform offers capabilities to prevent actions by scoring irreversibility and detecting risky browser states, pause high-impact actions for human approval, and prove compliance through an immutable audit trail of decisions, approvals, and blocks. Key security guarantees include zero-trust evaluation of every action before execution, synchronous execution hooks ensuring the agent cannot proceed until policies are checked, and local policy caching for fail-closed, offline enforcement without network dependency in the hot path. Reins also integrates with frameworks like Claude Code PreToolUse/PostToolUse hooks and OpenClaw, scanning configurations for OWASP ASI10 vulnerabilities and tracking agent drift over time. It can be installed via npm and includes a Claude Code Skill to provide agents with security posture awareness, making it a critical tool for governing and securing AI agent deployments in production environments.
https://github.com/pegasi-ai/reins
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...
Tencent/AI-Infra-Guard
AI-Infra-Guard is a full-stack AI red teaming platform providing comprehensive security analysis, vulnerability scanning, and jailbreak evaluation for AI ecosystems and LLMs.
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.