AI agent payment operations
Guardrails for AI agent payments.
Attribute every paid API call, tool purchase, and protocol payment to the agent, tool, and session that made it. Set budgets, enforce approvals before settlement, and reconcile the result — without holding your funds or private keys.
Non-custodialx402, MPP, AP2Budgets before settlement
PlatformSpend ControlGuardrails for AI agent payments.Now liveStillwellSleep stories, guided meditation, soundscapes — and Voice Stories text narration. No dark patterns.AvailableCrewProofScheduling and proof of service for cleaning teams.AvailableImgKit Gift StudioPersonalized digital gifts from one photo.
What Spend Control does
Spend Control stops AI agents from overspending by attributing every paid API call to an agent, tool, and session, then checking it against your budgets and approval rules before the money moves — and reconciling the result afterwards, without ever holding your funds or keys.
Autonomous agents spend real money — often with no one watching.
A single misconfigured agent can issue thousands of paid API calls without a human in the loop. Spend Control makes that spend visible and bounded before it becomes a bill. Read how on the blog →
Attribute
Know which agent, tool, and session initiated every paid call.
Control
Apply budgets, allowlists, and approval rules before money moves.
Reconcile
Verify settlement independently and export a defensible audit trail.
Practical guides to agent spend, payments, and audit.
Aug 11, 2026
Cost per Successful Task: Why Cheap-Per-Token Models Can Be More Expensive
Cost per successful task LLM: why cheap models can end up more expensive. Learn metrics, observability, and spend control strategies.
Read postAug 11, 2026
How to Safely Switch AI Models in Production: A Guide to Shadow Testing and Canary Rollouts
Safely switch AI models in production using shadow testing and canary rollouts to avoid regressions, cost spikes, and latency issues.
Read postAug 10, 2026
Audit Schema Implementation Guide: Transaction-Level Agent Auditing with @harpd/agent-transaction-audit-schema
Audit schema implementation guide for transaction-level agent auditing with @harpd/agent-transaction-audit-schema. Learn how to standardize AI agent audit trails, enforce spend control, and ensure compliance.
Read postOpen-source SDKs for agent observability, audit, and budget governance.
@harpd/observe
Zero-dependency transaction observability for AI agents.
agent-budget-policy
Declarative budgets and approval rules for agent payments.
x402-logging-middleware
Request/response logging for x402 payment flows.
agent-transaction-audit-schema
A portable schema for agent transaction audit trails.
mcp-paid-tool-starter
Starter kit for paid MCP tools and per-call billing.
More focused experiments from Harpd.
These products stand on their own for specific workflows. Spend Control is our platform bet; Labs are live experiments we keep honest.
Now live
Anyone who wants better sleep, calm, or text narrated aloud without subscription traps
Stillwell
Sleep stories, guided meditation, soundscapes — and Voice Stories text narration. No dark patterns.
Explore productAvailable
Cleaning and field-service teams
CrewProof
Scheduling and proof of service for cleaning teams.
Explore productAvailable
People creating meaningful gifts
ImgKit Gift Studio
Personalized digital gifts from one photo.
Open product ↗Harpd Spend Control, in plain terms
What does Harpd do?
Harpd builds Spend Control, a platform that puts guardrails around AI agent payments. It attributes every paid call to an agent, tool and session; enforces budgets and approvals before settlement; and reconciles the result — without holding your funds or private keys.
What is an AI agent payment?
An AI agent payment is a machine-initiated transaction where an autonomous agent pays for an API, tool or service on your behalf — using protocols like x402, MPP or AP2. Spend Control attributes and gates those payments.
How does Spend Control stop agents from overspending?
It intercepts paid calls before settlement. You set per-agent budgets, allowlists and an approval threshold; calls that exceed a limit are blocked or routed to a human for review, then every payment is reconciled against the policy afterwards.
Does Spend Control hold my money or private keys?
No. Spend Control is non-custodial. It observes and gates spend through your existing payment stack — it never takes custody of funds or signing keys, so there is no new counterparty risk.
Which AI agent payment protocols does it support?
Spend Control works across the three leading agent-payment protocols: x402, MPP and AP2. The same policy layer applies regardless of which protocol an agent uses to pay.
What is the difference between Observe and Enforce mode?
Observe mode attributes and reports spend with no blocking — safe to switch on immediately. Enforce mode applies budgets and approvals before settlement, actively preventing overspend. You can start in Observe and move to Enforce when confident.
Are Stillwell, CrewProof and ImgKit part of Spend Control?
No. They are separate products built under Harpd Labs: Stillwell (sleep and calm), CrewProof (cleaning crew scheduling and proof of service), and ImgKit Gift Studio (personalized digital gifts). Spend Control is the platform bet.
Get started
Start free