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
cuga-project/cuga-agent
CUGA is an open-source generalist agent harness designed to streamline the development and deployment of domain-specific enterprise agents. It provides a robust framework that handles agent and tool orchestration, planning logic, safety and alignment policies, and evaluation, allowing users to focus on configuring domain-specific tools, policies, and workflows. The platform integrates seamlessly with OpenAPI specs, MCP servers, and Langchain tools, facilitating rapid connection to various APIs and Python functions. CUGA offers configurable reasoning modes (fast, balanced, accurate) and supports hybrid API + browser tasks. Key features include multi-agent capabilities via CugaSupervisor, allowing for agent-to-agent communication and remote agents. A strong policy system enables configuration of agent behavior through five policy types: Intent Guard, Playbook, Tool Approval, Tool Guide, and Output Formatter, with human-in-the-loop approval for safe enterprise operations. CUGA also provides experimental save-and-reuse capabilities for execution paths, and agent skills that allow packaging domain workflows for on-demand discovery. It features a built-in knowledge engine for Retrieval-Augmented Generation (RAG) over various document types, with support for agent-level and session-level knowledge bases. For enterprise deployment, CUGA offers management and publishing tools with version control, and provides a Helm chart and scripts for self-hosting on Kubernetes clusters like kind, Minikube, Docker Desktop Kubernetes, GKE, EKS, or AKS.
https://github.com/cuga-project/cuga-agent
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.