AI agent governance · open source

Run AI agents like a workforce, not a wildfire.

Every agent works inside four rings of control. Point at one to watch it work; click to keep it.

four rings

Point at a ring above to see what it does. Click to keep it.

point at the agents · click for a pulse

try it

Now a floor of them. Make one misbehave.

Point at an agent to read its passport. Click it, then click a door to send it there, or press a button below to make one misbehave. Then switch the governance off and do it again.

simulation · drag to turn

make an agent

go deeper

The stack

Every service in its own room, with its drawing, its replay and the numbers behind it.

Walk the stack → read

Guides

How the pieces fit, written to be read in one sitting.

Open the guides → try

Live demo

The control room on a seeded fleet, in your browser.

Open the demo →

proof, not promises

Validated on real infrastructure. Then torn down.

Before this site existed, the stack ran on disposable boxes across Hetzner, AWS and GCP with a real Anthropic key. Then the same stack came up again as a five-node Kubernetes cluster on each of those three clouds.

8000/8000

Money, under load. Requests admitted against one budget, on a stub provider.

$0.00042

Money, per unit of work. The measured cost of one correctly resolved case.

2,449/s

Policy, throughput. Decisions a single pod makes each second.

Policy, under concurrency. Requests fired at once and sorted exactly right.

426B

Evidence, per decision. Hash-linked audit written for every decision rather than a sample.

12/12

Portability. Deliberate budget overruns blocked, identically on Hetzner, AWS and GCP.

25,586

Crypto inventory. Real Linux binaries scanned by Qryx, with zero crashes.

Rehearsal. Guardrail gaps across three hostile drills fired twice at a real gateway.

What is proven, claim by claim → How these numbers were produced

the people

Two of us, plus the agents.

This stack is written by two people who spend their working lives in exactly the two rooms it lives in: cloud security and cloud money.

author · cloud security & IAM

Yurii Kostiuk

Lead Security Architect · ex AWS Community Builder

IAM solutions architect and cloud security consultant: Zero Trust, identity, DevSecOps and platform resilience across AWS and GCP. The stack's view that an agent deserves a badge, a budget and a boundary comes straight from this desk.

IAMZero TrustCloud SecurityData SecurityCryptographyAWS / GCPKubernetesGo

CISSP · CCSP · TOGAF 9 · CKA / CKS · AWS SA Professional · Google Professional Cloud Architect

inConnect on LinkedIn

author · finops & cost governance

Tania Fedirko

FinOps Expert · AWS Community Builder

Cloud financial governance, cost optimization and multi-cloud strategy. Tania aligns engineering, finance and business, and applies FinOps practice to LLM APIs and token-based usage: the reason this stack meters money before it meters anything else.

FinOpsFinOps for AICost governanceMulti-cloudGreenOps

FinOps Certified Professional · FinOps Certified Practitioner

inConnect on LinkedIn