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
kenryu42/cc-safety-net
CC Safety Net — short for Coding CLI Safety Net — is a guardrail that runs on the execution path of AI coding agents. It installs as a PreToolUse hook and inspects every command an agent is about to run, blocking destructive operations such as recursive deletes of a home directory or a git checkout that discards uncommitted work, and refusing access to sensitive files including SSH keys and .env files. The central design claim is semantic parsing: instead of matching command strings against a blocklist, it analyses what a command actually does, so reordering flags, wrapping the call in a shell, or hiding it inside an interpreter one-liner does not slip past the check. The project was written in response to a well-publicised incident in which an agent wiped a user's home directory, and its stated position is that soft rules written into a CLAUDE.md or AGENTS.md file are advisory and cannot substitute for a hard technical constraint enforced at the point of execution. Coverage is broad across agent runtimes: documented installations exist for Claude Code, Codex, Cursor, Amp Code, Antigravity CLI, Gemini CLI, GitHub Copilot CLI, Hermes Agent, Kimi Code, OpenClaw, OpenCode and Pi, each wired through that tool's own hook mechanism. The implementation is TypeScript with continuous integration and coverage reporting, and configuration, reference material and the security model are documented on a dedicated site rather than in the README. It is MIT licensed and aimed at anyone running autonomous or semi-autonomous coding agents on a machine that holds work they cannot afford to lose.
https://github.com/kenryu42/cc-safety-net
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.