AgentPay
AgentPay's Team
Problem Statement
AI agents increasingly need to spend money autonomously — for APIs, subscriptions, and services. But giving an agent unrestricted wallet access is dangerous. There is no existing on-chain primitive that lets a human define scoped, time-limited, recipient-restricted spending permissions for an AI agent. AgentPay solves this with a smart contract that acts as a policy enforcer between the human and the agent.
Programmable ETH spending policies for AI agents on Base. Humans define strict rules — per-transaction limits, daily caps, approved recipient whitelists — enforced on-chain by a smart contract. The AI agent calls pay() and the contract enforces every limit automatically. No trust required.
Build Timeline
Team
AgentPay
admin
MandateIncrease your chances to win
- ›Most agents in the hackathon are exposed to prompt injection
- ›This might cause overspending and loss of funds
- ›Security is a crucial part of the hackathon
Share on X
Tell the world about this project
Intention
Plans to continue
Planning to extend AgentPay with USDC support, multi-agent coordination, and an MCP server so any AI agent can call pay() without writing code.