Agent Governance Toolkit

Programmable safety rails for LLM applications

NeMo Guardrails is NVIDIA's open-source toolkit for adding programmable safety rails to LLM applications. It supports five guardrail types — input, dialog, retrieval, execution, and output rails — covering content safety, jailbreak detection, topic control, PII masking, hallucination detection, and fact-checking. The toolkit uses Colang, a domain-specific language for defining conversational constraints, and integrates with OpenAI, Azure, Anthropic, HuggingFace, and LangChain/LangGraph.

Validate and structure LLM outputs with composable Guards

Guardrails AI is an open-source Python and JavaScript framework for validating and structuring LLM outputs using composable Guards built from a Hub of pre-built validators. It handles structured data extraction with Pydantic models, content safety checks including toxicity, PII detection, competitor mentions, and bias filtering, plus automatic re-prompting when validation fails. The Guardrails Hub offers dozens of validators from regex matching to hallucination detection via LLM judges.

Microsoft’s pytest-native red teaming framework for turning AI agent safety findings into CI tests.

RAMPART is an open-source Microsoft framework for safety and security testing of agentic AI applications. It brings red-team findings into a pytest-native workflow so teams can turn prompt injection, unsafe tool use, and behavioral boundary failures into repeatable regression tests. The strongest aicoolies angle is developer workflow: RAMPART makes agent safety part of CI/CD instead of a one-off security review.

Security scanner for MCP servers against tool poisoning attacks

MCP-Scan is a security tool that scans MCP servers for vulnerabilities including tool poisoning, prompt injection, cross-origin escalation, and rug pull attacks. Acquired by Snyk in 2026, it is the first dedicated security scanner for the MCP ecosystem. It analyzes tool descriptions, permissions, and behavior patterns to detect malicious or compromised MCP servers before they can exploit AI agents.

State-machine guardrails for controlling which tools AI coding agents can use at each phase.

Statewright is a guardrail layer for AI coding agents that uses explicit state machines to control what an agent can do at each stage of a workflow. Instead of relying only on prompt instructions, teams can model phases such as plan, implement, test, and review, then constrain tool access for clients like Claude Code, Codex, Cursor, opencode, and related MCP workflows.