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.
Awesome Infra for AI › AI Safety & Guardrails
data-privacy-stack/presidio
Presidio is a comprehensive, open-source SDK designed for data protection and de-identification of sensitive information (PII). Its core functionality revolves around the fast identification and anonymization of private entities found in various data types, including text, images, and structured data. It supports a wide range of PII categories, from credit card numbers and names to social security numbers and financial data. The framework offers several key features: it includes predefined and custom PII recognizers that utilize Named Entity Recognition (NER), regular expressions, rule-based logic, and checksums across multiple languages. It also provides options for connecting to external PII detection models, offering flexibility for different use cases. Presidio is highly customizable in both PII identification and de-identification processes, ensuring adaptability to specific business needs. It also includes a dedicated module for redacting PII text within images, including standard image types and DICOM medical images. The project aims to democratize de-identification technologies, facilitate transparent decision-making, and support both fully automated and semi-automated PII de-identification flows across various platforms, from Python and PySpark workloads to Docker and Kubernetes deployments. The project emphasizes extensibility and encourages community contributions.
https://github.com/data-privacy-stack/presidio
Also in AI Safety & Guardrails
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.
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.