Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/microsoft/agent-governance-toolkit/llms.txt

Use this file to discover all available pages before exploring further.

The Agent Governance Toolkit (AGT) solves the hardest unsolved problem in production AI: how do you make an autonomous agent incapable of misbehaving? When agents call tools, browse the web, query databases, and delegate to other agents, prompt-level safety instructions are not a control surface — they are polite requests to a stochastic system. OWASP LLM01:2025 states this explicitly, and published research (Andriushchenko et al., ICLR 2025) reports a 100% attack success rate against GPT-4o, GPT-3.5, Claude 3, and Llama-3 under adaptive attacks. AGT does not try to win that fight inside the prompt. Every tool call, message send, and agent delegation is intercepted in deterministic application code before the model’s intent reaches the wire. Actions the AGT policy engine denies are not “unlikely.” They are structurally impossible.
AGT is currently in Public Preview — production-quality releases with possible breaking changes before GA.

The Core Architecture

AGT inserts a mandatory governance gate between your agent and the outside world. The flow is:
Agent ──► Policy Engine ──► Identity ──► Audit Log
            (YAML/OPA/Cedar)  (SPIFFE/DID/mTLS)  (Tamper-evident)
                 │                                      │
                 ├── Allowed ──► Tool executes           │
                 └── Denied  ──► GovernanceDenied        │

                                                 Decision Record
Every layer is optional. Start with govern() and add layers as your risk profile grows. Most teams run policy enforcement plus audit logging and never need the full stack. Policy Engine evaluates every action against your YAML, OPA/Rego, or Cedar rules before execution — in under 0.1 ms. Identity assigns each agent a cryptographic credential (Ed25519 / SPIFFE / DID) and a 0–1000 trust score so you always know which agent acted. Audit Log writes a tamper-evident, Merkle-chained decision record for every allow and deny — what policy was active, what was requested, and why.

The Key Differentiator

Probabilistic Filtering

Model-layer safety relies on the LLM choosing to follow rules. Adversarial inputs can circumvent it. Attack Success Rate (ASR) is the canonical metric for this class of failure — and it is non-zero by construction.

Deterministic Interception

AGT intercepts at the application middleware layer. A denied action never reaches the wire. There is no probability involved — the governance gate either allows or it doesn’t.
When AGT denies an action, that denial is enforced in deterministic application code — the same trust boundary used by every Python-based agent framework. It is not a recommendation to the model; it is a hard stop in the execution path.

Supported Languages

AGT ships first-class governance packages in five languages. All five implement the core governance primitives: policy evaluation, agent identity, trust scoring, and audit logging.
LanguagePackageInstall
Pythonagent-governance-toolkitpip install agent-governance-toolkit[full]
TypeScript@microsoft/agent-governance-sdknpm install @microsoft/agent-governance-sdk
.NETMicrosoft.AgentGovernancedotnet add package Microsoft.AgentGovernance
Rustagent-governancecargo add agent-governance
Goagent-governance-toolkitgo get github.com/microsoft/agent-governance-toolkit/agent-governance-golang
Python is the primary implementation and includes the full stack. See the Language Package Matrix for detailed per-language feature coverage.

Package Overview

AGT is structured as a set of composable packages. Each addresses a distinct governance concern.
PackageDescription
Agent OSPolicy engine, agent lifecycle, governance gate
Agent Control SpecificationStateless, deterministic, fail-closed policy decision runtime (Rust core)
Agent MeshAgent discovery, routing, and trust mesh
Agent RuntimeExecution sandboxing with four privilege rings
Agent SREKill switch, SLO monitoring, chaos testing
Agent ComplianceOWASP verification, policy linting, integrity checks
Agent MarketplacePlugin governance and trust scoring
Agent LightningRL training governance with violation penalties
Agent HypervisorExecution audit, delta engine, commitment anchoring, command denylist enforcement

Additional Capabilities

CapabilityDescription
MCP Security GatewayTool poisoning detection, drift monitoring, typosquatting, hidden instruction scanning
Shadow AI DiscoveryFind unregistered agents across processes, configs, and repos
Governance DashboardReal-time fleet visibility for health, trust, and compliance
PromptDefense Evaluator12-vector prompt injection audit
Contributor ReputationPR/issue author screening for social engineering

Framework Support

AGT integrates with every major agent framework through middleware adapters. You can wrap any tool function in two lines, or use a framework-specific adapter for deeper integration.

Microsoft Agent Framework

Native Middleware

Semantic Kernel

Native (.NET + Python)

AutoGen

Adapter

LangChain / LangGraph

Adapter

CrewAI

Adapter

OpenAI Agents SDK

Middleware

Google ADK

Adapter

LlamaIndex

Middleware

Claude Code

Governance plugin package
Additional adapters available for: Haystack, Mastra, Dify, smolagents, PydanticAI, Anthropic, Gemini, Mistral, and more.

Standards Compliance

AGT is built to satisfy real-world compliance requirements, not just check boxes:
StandardCoverage
OWASP Agentic AI Top 10All 10 ASI risk categories with deterministic controls
NIST AI RMF 1.0Full GOVERN, MAP, MEASURE, MANAGE alignment
EU AI ActCompliance mapping with automated evidence
SOC 2Control mapping with audit trail export
AARM ExtendedAll R1–R9 requirements satisfied
ATFAll five elements mapped

Next Steps

Quickstart

Govern your first agent tool call in under 5 minutes with a YAML policy and the govern() wrapper.

How It Works

Deep dive into AGT’s deterministic interception architecture, trust scoring, and security model.

Build docs developers (and LLMs) love