Control every dollar your AI agent spends

Set budgets, define spending policies in plain English, and approve or reject AI agent purchases in real time — before the money leaves your account.

AI agents are spending money on your behalf.
Do you know where it goes?

$

Uncontrolled spending

Agents call APIs, provision cloud resources, and subscribe to SaaS tools — often without explicit limits.

?

No visibility

You find out about costs after the fact — when the invoice arrives. By then it's too late.

!

No policy enforcement

Prompt instructions like "don't spend more than $50" are suggestions, not guarantees. Agents can ignore them.

How it works

LetAgentPay sits between your AI agent and the payment — a policy checkpoint that enforces your rules.

1

Define policies

Set budgets, category limits, schedules, and per-request caps — in plain English or JSON.

2

Agent requests

Before spending, your agent calls LetAgentPay with the amount, category, and description.

3

Policy check

8 checks run instantly: budget, category, limits, schedule, spending history. Auto-approve or escalate.

4

You decide

Approved requests proceed. Flagged ones wait for your review. Rejected ones stop the agent.

Where LetAgentPay fits in the payment lifecycle

We're not a payment processor. We're the policy layer that decides whether a payment should happen.

AI Agent
wants to spend
LetAgentPay
policy check
Payment
approved spend

Before payment

The agent asks LetAgentPay for approval before initiating any transaction. No approval — no payment.

Real-time decisions

Policies are checked instantly. Auto-approve for routine purchases, escalate unusual ones to you.

After payment

The agent confirms the result. Spending counters update. Full audit trail preserved.

Capabilities

Natural language policies

Write rules like "max $100/day on cloud services, no weekend spending". AI converts them to enforceable JSON policies.

Multi-level budgets

Set per-request, daily, weekly, monthly limits and an overall budget. All checked in real time against actual spending.

Category controls

Restrict agents to specific spending categories — groceries, cloud, SaaS, travel — and set different limits per category.

Schedule-based rules

Allow spending only during business hours, block weekends, or define custom time windows.

Auto-approve & escalation

Routine purchases within policy get approved instantly. Unusual or high-value requests require your manual review.

Real-time dashboard

See every request as it happens. Approve, reject, or review with full context — amount, category, merchant, policy check results.

Spending analytics

Track daily, weekly, and monthly spending by agent. See budget utilization and remaining balances at a glance.

Full audit trail

Every request, every policy check, every decision — logged and searchable. Know exactly what was spent, when, and why.

x402 crypto-micropayments

Authorize on-chain USDC payments on Base. Same policy engine for fiat and crypto — unified budget, one dashboard.

Integrate in minutes

Three ways to connect your agent — pick what fits your stack.

Python SDK

pip install letagentpay

client = LetAgentPay(
    token="agt_..."
)
client.purchase(
    amount=49.99,
    category="cloud"
)

MCP Server

Works with Claude Desktop, Cursor, and any MCP-compatible AI tool. One config line — your agent gets spending tools automatically.

REST API

Simple HTTP endpoints with Bearer token auth. Works with any language or framework. Full OpenAPI spec available.

Built for

AI agent developers

Give your users confidence that their agent won't overspend. Add spending controls as a feature, not a liability.

Teams using AI tools

Let agents handle procurement, cloud provisioning, and SaaS subscriptions — with guardrails you define.

Individuals with AI assistants

Trust your personal AI to book, shop, and subscribe — knowing every purchase gets checked against your rules first.

Start controlling AI spending today

Free while in early access. Set up in under 5 minutes.