CUSTODIAN
Autonomous Spend Authority
NemoClaw kernel sandbox
Nous Hermes Agent
Stripe real PaymentIntents

The first AI agent you can hand a real wallet to.

Custodian is the trust layer underneath: kernel-enforced authority, not a promise in a prompt. The agent itself cannot exceed its limit or approve its own escalation — even if it tries. Below: a real agent — protecting ArgoBox, a real production homelab — proving it, live.
AUTHORITY · PER-ACTION · SESSION · ENFORCED AT KERNEL LEVEL
Agents that get broad real access are unreliable today — not malicious, just unreliable. That's not a guess; it's what operators already running agents against real systems report firsthand. The question that actually matters isn't "will it make a mistake," it's "can a mistake cost real money." Custodian is the answer to that second question: a kernel-enforced ceiling an agent cannot talk its way past, with a real human out-of-band the only path beyond it. It's infrastructure for any team — an MSP, a fintech, anyone giving an agent real account access — that needs that guarantee before they'll let an agent near a real account at all.
OPS / INFRA — would this break something?
signal:
source:10.0.0.199:8093 (real infra API)
FINANCE — is it worth the cost?
amount:
artifact:
SECURITY — does kernel policy allow it?
enforcement:kernel (Landlock + OPA)
artifact:
Authority Band
Per-Action Cap
Autonomous Spend
Sandbox
checking…
Live Audit Feed — Ops Decisions & Spend
Waiting for events…
Kernel-Level Policy Enforcement — Raw OCSF Log (NemoClaw / OpenShell)
Waiting for sandbox activity…
Try It Yourself — Live Decision Engine
⚠ ESCALATION — HUMAN APPROVAL REQUIRED
This exceeds the agent's autonomous authority band.
A one-time approval code has been dispatched to the human operator.
STEP 1/6
🤖 Nemotron 3 Super — live