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
SponsioLabs/Sponsio
Sponsio is an open-source project focused on bringing deterministic safety solutions to probabilistic AI agents. It allows for the enforcement of 'agent contracts' – runtime rules checked at every agent action – with extremely low latency (p50 of 0.139 ms) and without incurring additional LLM costs during the hot path. These contracts are backed by formal methods and provide robust guardrails against misaligned or malicious agent behavior. The project demonstrates significant improvements in preventing agent misalignment and fraud, citing benchmarks where it avoids 95.6% of misalignment on average and blocks 18/19 fraud scenarios in financial audits. It operates by compiling natural language rules and pattern libraries into contracts that are enforced by a Fuzzy LTL Monitor, deciding to pass, block, warn, escalate, or redirect function calls. Sponsio is designed to integrate with popular agent frameworks like LangChain, Claude Agent, OpenAI Agents, Google ADK, CrewAI, and Vercel AI, supporting both Python and TypeScript. It offers a quick start with single prompts or CLI commands for onboarding and provides a library of pre-built contract bundles for common safety scenarios, allowing users to guard their agents against known failure classes with minimal configuration. This tool is crucial for operationalizing AI agents safely and securely in production environments.
https://github.com/SponsioLabs/Sponsio
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.