Agreed. We've been thinking about this exact problem.

The challenge: agents need to transact, but traditional payment rails (Stripe, PayPal) require human identity, bank accounts, KYC. That doesn't work for autonomous agents.

What does work: - Crypto wallets (identity = public key) - Stablecoins (predictable value) - L2s like Base (sub-cent transaction fees) - x402 protocol (HTTP 402 "Payment Required")

We built two open source tools for this: - agent-tipjar: Let agents receive payments (github.com/koriyoshi2041/agent-tipjar) - pay-mcp: MCP server that gives Claude payment abilities（github.com/koriyoshi2041/pay-mcp)

Early days, but the infrastructure is coming together.

I am genuinely curious - what do you see as the difference between "agent-friendly payments" and simply removing KYC/fraud checks?

Like basically what an agent needs is access to PayPal or Stripe without all the pesky anti-bot and KYC stuff. But this is there explicitly because the company has decided it's in their interests to not allow bots.

The agentic email services are similar. Isn't it just GSuite, or SES, or ... but without the anti-spam checks? Which is fine, but presumably the reason every provider converges on aggressive KYC and anti-bot measures is because there are very strong commercial and compliance incentives to do this.

If "X for agents" becomes a real industry, then the existing "X for humans" can just rip out the KYC, unlock their APIs, and suddenly the "X for agents" have no advantage.