The Autonomous Stack

Business & Finance · Payments & Usage · v1.0.0

Agent Usage Meter v1.0

Turn raw agent tool-call logs into billable evidence *before* anything is charged. The pack reads a local usage ledger and emits deterministic billable totals plus every exception that must be resolved first: over-quota calls, duplicate events, missing authorizations, and reconciliation gaps.

$3.00one-timePay with crypto

usage-metering billable-evidence quota-enforcement payment-authorization byo-llm

agent ⟶ theautonomousstack.xyz

01GET /api/v1/pack/agent-usage-meter-v1

402 Payment RequiredX-PAYMENT-REQUIRED

02sign TransferWithAuthorization3.00 USDC · Base (eip155:8453)

03GET + PAYMENT-SIGNATURE

200 OKapplication/zip · 19 files

pay per pack over x402no account

What's inside

Who it is for

API and MCP providers who sell metered access to autonomous agents, and platform teams who bill agent tool calls per unit. If your meter and your payment authorizations disagree, you either under-bill or charge for usage you cannot defend. This pack finds the disagreement first.

Quick start

sudo bash install.sh --no-service
cp examples/usage_ledger.json my_ledger.json
./venv/bin/python agent.py --ledger my_ledger.json meter
./venv/bin/python agent.py --ledger my_ledger.json report --out usage_report.md

Each usage event needs event_id, customer_id, sku, a numeric quantity, an ISO timestamp, and the authorization_id that covers it. Anything missing or unreadable becomes an exception, never a silent charge.

local usage_ledger.json
        |
        v
deduplicate --> check authorization --> price and meter --> reconcile quota + authorized amount
                                                                    |
                                              billable evidence -----+--> Markdown / JSON report
                                                                    |
                                                                    +--> optional BYO-LLM brief

What lands in each bucket

Bucket Meaning
billable_totals Units per customer and sku that survived every gate, with the amount pending approval
over_quota Metered usage above included_units, flagged when a hard cap is crossed
duplicate_events A repeated event_id, or a new id replaying an identical call
missing_authorizations Usage with no, unknown, inactive, or mismatched payment authorization
reconciliation_gaps Out-of-period events, unpriced skus, missing entitlements, exceeded authorizations
manual_review Records whose source data is ambiguous, echoed unchanged

Honest operating modes

Capability Deterministic core Optional BYO-LLM
Deduplication, quota and authorization checks Yes Not needed
Pricing arithmetic and billable totals Yes Not needed
JSON and Markdown reports Yes Not needed
Prioritized human-readable metering brief Template summary Claude Code, Kimi Code, or Codex CLI

No API key or network call is required. The optional CLI uses the subscription already connected on the machine. This agent produces evidence: it never charges a card, captures a payment, issues an invoice, or changes a customer account.

Commands

python agent.py --ledger my_ledger.json meter
python agent.py --ledger my_ledger.json --period-start 2026-07-01 --period-end 2026-07-31 meter
python agent.py --ledger my_ledger.json report --out usage_report.md
python agent.py --ledger my_ledger.json brief
python agent.py status
python test_agent.py

See CUSTOMIZE.md to connect your own event stream and CHECKLIST.md before you bill from the output.