Agent Governance Foundation

Blog

Writing on Agent Identity, Policy & Audit

Thinking on agent governance, open standards, and the infrastructure we need to build. No announcements, no marketing — just the technical work.

How to Add Authorization Gates to OpenAI Agents SDK Tools

OpenAI's Agents SDK ships its own tool guardrail hook. Here's why we didn't build on top of it, what we built instead, and the one real caveat worth knowing before you turn on outcome reporting.

Read post
openai-agents-sdkauthorizationpythonintegration

How to Add Authorization Gates to LangGraph Agents

LangGraph gives you two different places to put an agent's logic — a tool-calling node and an arbitrary graph node — and they need two different authorization patterns. Here's both, plus the one shape that needs a third.

Read post
langgraphauthorizationpythonintegration

Authorizing AWS Lambda Agents: Containers, Chains, Guards

What changes when an AI agent runs in AWS Lambda: reused containers, short-lived delegation chains, and what a guard on a handler does and does not decide.

Read post
aws-lambdaauthorizationarchitectureagent-governance

agf-sdk 0.7.0: New Adapters and a Warm-Container Fix

Two new framework adapters, plus a real correctness fix for a broken sync/async bridge that crashed anything reusing an AGF client across repeated calls — Lambda, long-running workers, notebook sessions.

Read post
agf-sdkreleasepython

Explainability Tells You Why. Authority Tells You Whether.

As AI agents move from answering questions to taking actions, explainability stops being enough. Organizations need to answer a different question: did the agent actually have the authority to act?

Read post
governanceauthorizationidentity

AGF Specifications Are Public: 27 Open Standards for Agents

Every AGF specification — delegation tokens, chains, trust zones, revocation, audit, and protocol adapters for MCP, A2A, and HTTP — is now published under Apache 2.0 at github.com/agent-governance-foundation/agf-standards, with an open RFC process and a conformance path for independent implementations.

Read post
standardsopen-sourceannouncementgovernance

HTTP Agent Authorization for Agents Beyond MCP and A2A

MCP and A2A give agents standard tool-calling and delegation protocols. Plenty of agents still just call a plain REST API — internal microservices, third-party SaaS, GraphQL endpoints. The AGF HTTP Gateway fronts those, too, without requiring the downstream API to change.

Read post
restauthorizationarchitecturegateway

Authorizing Browser Agents: Guarding Page Actions

MCP, A2A, and REST gateways all work by fronting a downstream server. A browser-automation agent has no downstream server — it drives a local browser directly. Here's how AGF governs that case instead.

Read post
browserplaywrightauthorizationpythonintegration

A2A Agent Authorization: Who May Delegate to Whom

The Agent2Agent protocol standardizes how one agent discovers and delegates work to another. It doesn't standardize whether that delegation should be allowed. Here's how the AGF A2A Gateway closes that gap.

Read post
a2aauthorizationarchitecturegateway

MCP Authorization: Deciding Which Tool Calls May Run

The Model Context Protocol standardizes how agents discover and call tools. It doesn't standardize whether they should be allowed to. Here's how the AGF MCP Gateway closes that gap — register your MCP server, and every tool call gets a real authorization decision before it executes.

Read post
mcpauthorizationarchitecturegateway

CISO Brief: The Actual Attack Surface of Deployed Agents

'What if the AI does something bad' is too vague to build a security program around. Here are the four attack patterns that actually show up in agent deployments, and the controls that address each one.

Read post
ciso-briefsecurityattack-surfacerevocationexecutive

CISO Brief: Agent Audit Mapped to NIST, ISO 42001, EU AI Act

Auditors don't ask about your model's benchmark scores. They ask who did what, when, under what authority, and whether you can prove it. Here's how AGF's audit artifacts map to the three frameworks compliance teams are actually being asked about.

Read post
ciso-briefcomplianceauditnistiso42001eu-ai-actexecutive

CISO Brief: What 'Securing AI Agents' Actually Means

Most 'AI security' conversations are still about model safety — jailbreaks, hallucinations, prompt injection. That's not the same problem as securing what an agent is authorized to do once it's deployed. Here's the distinction, and the control surface that matters.

Read post
ciso-briefsecurityauthorizationidentityexecutive

Agent Identity vs Authorization: Who It Is, What It May Do

Oktane 2026 is billing itself as the AI security event of the year, with a simple tagline: agents change everything. We agree — and think the industry conversation is about to split into two layers: who an agent is, and what it's allowed to do.

Read post
oktaidentityauthorizationindustry

Authorizing Tool Calls in AutoGen Multi-Agent Systems

AutoGen's function_map has no authorization concept — any registered function is one tool call away from execution. Here's how to gate it with the INTREXA AXIS SDK, no framework-specific adapter required.

Read post
autogenauthorizationpythonintegrationmulti-agent

Adding Authorization Gates to CrewAI Crews and Tools

CrewAI's Agent/Task/Crew model has no built-in concept of policy enforcement — every tool call an agent makes is implicitly trusted. Here's how to gate CrewAI tool calls with AGF in a few lines.

Read post
crewaiauthorizationpythonintegration

Introducing agf-sdk: the INTREXA AXIS SDK on PyPI

The Python SDK for INTREXA AXIS is now published on PyPI. One package, three ways to call it: a synchronous facade, an async client, and framework adapters for LangChain and CrewAI.

Read post
sdkpythonreleaseannouncement

The Delegation Problem: When Agents Spawn Other Agents

Multi-agent systems inherit a centuries-old problem: how do you ensure that what the subordinate does is what the principal actually authorized? This isn't a technical problem — it's a governance one.

Read post
delegationmulti-agentauthorizationarchitecture

Authorizing LangChain Agents: Where the Check Belongs

Where should authorization sit in a LangChain agent, and what should the check decide? A design guide to placement, granularity and limits.

Read post
langchainauthorizationarchitectureagent-governance

What Is AI Agent Governance? A Practical Introduction

Everyone is talking about AI governance. But agent governance is a specific discipline within that — one most organizations aren't ready for yet. Here's what it actually means and why it's different.

Read post
governanceintroductioncomplianceidentity

The Audit Problem: Why Agent Actions Are Hard to Trace

Most organizations deploying AI agents today cannot answer a simple question: what did the agent do, and why? This post explains why that's the case and what a real audit trail looks like.

Read post
auditcomplianceobservability