Budget Controls in PaperclipAI: Hard Caps, Soft Alerts, and Auto-Pause
Runaway AI costs are a legitimate concern. PaperclipAI addresses it at the infrastructure level with two-tier budget enforcement: soft warnings at 80% and hard stops at 100%. An agent that hits its budget limit is automatically paused — no heartbeats fire, no tokens consumed, no costs incurred.
How budget enforcement works
| Threshold | Action | What Happens to the Agent |
|---|---|---|
| 80% of budget | Soft alert | Agent is instructed to focus on critical tasks only |
| 100% of budget | Hard stop | Agent is auto-paused — no more heartbeats fire |
| Budget increased | Resume | Agent returns to active state |
| Calendar month resets | Auto-resume | Monthly budgets reset, agents reactivate |
Two levels of budget control
- Company-level: Set via API — PATCH /api/companies/{companyId} with budgetMonthlyCents — caps total organization spend
- Per-agent: Set through agent settings or API — caps individual agent spend regardless of company budget
Visibility into spending
Three API endpoints and a dashboard provide cost visibility: company totals, per-agent breakdowns, and per-project spending. The dashboard shows current-month spend against budgets in real time. No surprises, no hidden costs, no ambiguity about where tokens are going.
Keep reading
PaperclipAI Is Free. Your AI Provider Bill Is Not. Here's the Real Cost Breakdown.
PaperclipAI is open-source — the platform itself costs nothing. Your costs are AI provider API usage (tokens), hosting, and your time. Here's what the real spending looks like.
Running PaperclipAI 24/7: Heartbeats, Budget Limits, and Unattended Operation
PaperclipAI agents run on heartbeat schedules with budget auto-pause. Overnight operation is safe because the system has hard limits — agents can't run forever or spend infinitely.
Want to talk about what AI can do for your business?
30 minutes, no sales pitch. Just an honest conversation about where AI can move the needle for you.
Book a Free Call