ActOnce Spend Gateway
Open-source spending controls for AI agents
ActOnce Spend Gateway gives AI agents spending rules to follow before a purchase goes ahead. Set purchase limits, choose trusted merchants, block spending categories and require human approval above your chosen threshold.
Built for developers, solo builders and teams using MCP-compatible agents such as OpenClaw and Hermes, it checks purchase requests and returns a clear decision: approve, reject or request approval.
The core gateway is open source, MIT-licensed and runs locally. It does not process payments or handle payment credentials. Paid plans add hosted dashboards and team controls.
Features
Custom spending rules: Define purchase limits, merchant allowlists, category blocks and permitted spending hours in a YAML file.
Human approval: Queue requests that exceed your approval threshold for review before proceeding.
Duplicate detection: Catch repeated purchase requests within a configurable time window.
MCP integration: Connect to MCP-compatible AI agents, including OpenClaw and Hermes.
Local operation: Keep the core gateway's policy files, logs and duplicate detection database on your machine.
No payment credentials: The gateway makes approval decisions without handling card details or payment tokens.
CLI and simulation mode: Check requests from the command line and test policies before using them.
Open-source foundation: Use, modify and self-host the MIT-licensed core.
Paid plans for teams: Add hosted dashboards, team approvals, client and project tagging, and webhook integrations.
Use Cases
Domain purchases: Allow an agent to request domains from approved registrars within a set purchase limit, with larger requests sent for approval.
Development purchases: Check requests for software subscriptions, hosting upgrades or other development resources against your spending policy.
Agency workflows: Apply spending controls to agents working across client projects, with tagging and shared approvals on the Team plan.
Purchases outside working hours: Restrict when agents can receive automatic approval and flag requests that need your attention.
Repeated requests: Catch duplicate purchase attempts caused by retries or overlapping agent tasks.
Testing agent workflows: Use simulation mode to see how spending rules respond before connecting the workflow to a payment tool.
Comments
I've been building with AI agents and exploring how much responsibility we can give them. Spending money is where that gets particularly interesting. "Buy a domain for this project" sounds straightforward. But which merchant can the agent use? How much can it spend? What happens if it retries the same purchase? Telling an agent to be careful doesn't answer those questions. I wanted spending rules that sit outside the prompt, with a clear point where the agent has to ask for permission. That's why I built ActOnce Spend Gateway. You set the rules: purchase limits, trusted merchants, blocked categories and thresholds for human approval. The gateway checks purchase requests and returns a decision: approve, reject or ask you. It doesn't process payments or handle your card details. Your chosen payment tool handles the transaction. The core is MIT-licensed and runs locally, with duplicate detection, an approval queue and MCP support. There are also paid plans for hosted dashboards and team controls. My aim is to give agents useful independence while keeping people in charge of the money. I'd love to hear from other builders: what would you let an agent buy today, and what would you always want to approve yourself?
Premium Products
Sponsors
Buy
Makers
Makers
Comments
I've been building with AI agents and exploring how much responsibility we can give them. Spending money is where that gets particularly interesting. "Buy a domain for this project" sounds straightforward. But which merchant can the agent use? How much can it spend? What happens if it retries the same purchase? Telling an agent to be careful doesn't answer those questions. I wanted spending rules that sit outside the prompt, with a clear point where the agent has to ask for permission. That's why I built ActOnce Spend Gateway. You set the rules: purchase limits, trusted merchants, blocked categories and thresholds for human approval. The gateway checks purchase requests and returns a decision: approve, reject or ask you. It doesn't process payments or handle your card details. Your chosen payment tool handles the transaction. The core is MIT-licensed and runs locally, with duplicate detection, an approval queue and MCP support. There are also paid plans for hosted dashboards and team controls. My aim is to give agents useful independence while keeping people in charge of the money. I'd love to hear from other builders: what would you let an agent buy today, and what would you always want to approve yourself?
Premium Products
New to Fazier?
Find your next favorite product or submit your own. Made by @FalakDigital.
Copyright ©2026. All Rights Reserved