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
cordum-io/cordum
Cordum is a source-available "Agent Control Plane for Governance, Safety, and Trust" that sits between AI agents (including local tools such as Claude Code) and the actions they take, so that risky operations require an approval step instead of running unchecked. It includes Cordum Edge, described as a compliance firewall for Claude Code and other local AI-agent actions. The stack is composed of several Go services: an API gateway, a scheduler, a safety kernel, a workflow engine, a context engine, a dashboard, NATS for messaging, and TLS-secured Redis, all communicating over the CAP v2 protocol. A one-command quickstart script stands up the full stack with auto-generated secrets, auto-provisioned TLS certificates, and a post-deploy smoke test that exercises a real approval-gate workflow end to end. The project also ships pre-built, cosign-signed multi-arch container images (api-gateway, scheduler, safety-kernel, workflow-engine, context-engine, mcp, dashboard) that can be run via Docker Compose or installed into Kubernetes through an official Helm chart, with configurable ingress and secret handling for production deployments. The dashboard provides a web UI (default admin login, or API-key login) for observing and approving agent actions. Cordum targets engineering and security teams that run AI coding agents or autonomous agents against real systems and need a policy-enforcement and audit layer — approval gates, safety checks, and a firewall on agent-initiated actions — rather than trusting the agent's own judgment or a wrapper around a single tool.
https://github.com/cordum-io/cordum
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.