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
agentcontrol/agent-control
Agent Control is an open-source project designed to provide a centralized control plane for governing the runtime behavior of AI agents at scale. Its core purpose is to enforce guardrails and safety policies without requiring modifications to the agent's underlying code. It achieves this by evaluating inputs and outputs against configurable rules, effectively blocking common threats such as prompt injections and PII leakage. The platform supports defining controls once and applying them across multiple agents, allowing for updates without redeploying agents. Controls can be managed via API or a UI, offering flexibility in configuration. Agent Control includes pluggable evaluators for various patterns (regex, list, JSON, SQL) and also allows users to bring their own custom evaluators. It integrates with popular agent frameworks like LangChain, CrewAI, Google ADK, and AWS Strands. The project emphasizes centralized safety, runtime configuration, and extensibility. It offers an SDK for Python and TypeScript to wrap model or tool calls with control logic and register agents. The platform also includes observability features, allowing external integrations to sink control-event payloads and support OpenTelemetry for tracing. This makes Agent Control a critical tool for organizations looking to deploy AI agents responsibly and securely in production environments.
https://github.com/agentcontrol/agent-control
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.