Capri AgentPay is the governed payment layer for AI agents. As agents start calling paid APIs and settling transactions on their own, handing them a private key is a security nightmare—one bad prompt can drain a wallet. Capri puts a runtime between the agent and the signer.

The agent calls one typed surface. When it hits an HTTP 402 Payment Required challenge, Capri evaluates your policy in a fixed order: merchant allowlist, per-transaction cap, daily budget, then an auto-approve threshold that can pause for human review. Only when every check passes does it settle, retry the original request with proof attached, and store a signed receipt you can verify offline.

Features: x402 handling, per-agent budgets and caps, merchant allowlists, human-in-the-loop approvals, verifiable receipts, six MCP tools instead of raw key access, a VS Code extension, and Base Sepolia sandbox settlement. Agents never hold your keys—every payment is policy-checked before a signature ever exists.

Capri AgentPay is the governed payment layer for AI agents. As agents start calling paid APIs and settling transactions on their own, handing them a private key is a security nightmare—one bad prompt can drain a wallet. Capri puts a runtime between the agent and the signer.

The agent calls one typed surface. When it hits an HTTP 402 Payment Required challenge, Capri evaluates your policy in a fixed order: merchant allowlist, per-transaction cap, daily budget, then an auto-approve threshold that can pause for human review. Only when every check passes does it settle, retry the original request with proof attached, and store a signed receipt you can verify offline.

Features: x402 handling, per-agent budgets and caps, merchant allowlists, human-in-the-loop approvals, verifiable receipts, six MCP tools instead of raw key access, a VS Code extension, and Base Sepolia sandbox settlement. Agents never hold your keys—every payment is policy-checked before a signature ever exists.