Spend Control for Open WebUI
Open WebUI is the open-source frontend for local and hosted LLMs — chat, agents, and tool pipelines. The frontend is free; the agents behind it spend.
Why Open WebUI agents spend
Agents and pipelines call paid APIs and tools.
Multi-user deployments multiply usage.
Local models still call paid tools beyond inference.
How it works
Wire the guard into your agents and pipelines: before any spend, they ask sipi.bot and get a deterministic decision.
Rules that fit
Per-user or per-pipeline daily ceiling.
Merchant allowlist for paid tools.
Velocity limit on retry loops.
Guard call
import requests
r = requests.post("https://sipi.bot/v1/transactions/evaluate",
json={"amount": 10, "merchant": "api.vendor.com", "category": "api"},
headers={"Authorization": "Bearer KEY"})
decision = r.json()["decision"]Your frontend, our gate.
FAQ
Does this work with local models?
Yes — the firewall governs tool and API spend regardless of inference location.
Can I cap per user?
Yes — per-agent rules per user or pipeline.
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