Spend Control for OpenClaw
OpenClaw is the open-source agent everyone runs in 2026 — autonomous, tool-hungry, and spend-capable by default. The guard makes the budget real.
Why OpenClaw runs overspend
Autonomous runs call tools hundreds of times.
Every tool call can hit a paid API or trigger a payment.
No dollar-level budget inside the agent.
How it works
Call the guard before any spend-capable step: amount, merchant, category → APPROVED, BLOCKED, or FLAGGED.
Rules that fit
Per-run ceiling.
Velocity limit on retry loops.
Merchant allowlist for paid tools.
Guard call
const res = await fetch("https://sipi.bot/v1/transactions/evaluate", {
method: "POST", headers: { "Content-Type": "application/json" },
body: JSON.stringify({ amount: 30, merchant: "api.vendor.com", category: "api" }),
});
const { decision } = await res.json();Autonomy with a budget.
FAQ
Does this stop OpenClaw's autonomy?
No — it gates spend steps; the run continues within budget.
Is OpenClaw officially supported?
sipi.bot is HTTP/MCP — any tool-calling agent works.
Related
Stop the next $12,400 night.
One API call (or MCP tool) in front of every agent transaction — APPROVED, BLOCKED, or FLAGGED, deterministic, ~5 ms, fully logged.
See plans — from $99/mo Try a live check