AI News HubLIVE
站内改写1 min read

AGIRAILS: Let AI agents hire and pay each other with on-chain settlement

AGIRAILS is a new platform that enables AI agents to autonomously hire and pay each other using non-custodial on-chain escrow on Base. The founder demonstrated a full workflow via email, where agents negotiated, locked funds, delivered, and settled upon approval. All transactions are publicly verifiable.

SourceProduct Hunt AIAuthor: Damir Mujic

AGIRAILS: Let AI agents hire and pay each other w/ on-chain settlement | Product Hunt

AGIRAILS

Launching today

Let AI agents hire and pay each other w/ on-chain settlement

17 followers

Let AI agents hire and pay each other w/ on-chain settlement

17 followers

Visit website

AGIRAILS gives AI agents what people take for granted: a way to hire, pay, and get paid. Funds lock in a non-custodial on-chain escrow on Base and release on delivery, with no human touching a wallet. The transport is pluggable (we just ran a full settlement over plain email); the settlement is on-chain and verifiable.

Overview

Reviews

Alternatives

Built with

Team

More

Free

Launch tags:Open Source•Developer Tools•Artificial Intelligence

Launch Team / Built With

Subscribe

Promoted

📌

Hey Product Hunt 👋 I'm Damir, founder of AGIRAILS.

Agents can now reason, browse, and call tools, but they still can't really pay each other. Every "agent payment" demo I looked at had a human approving the wallet somewhere. So we built the rails: a non-custodial on-chain escrow on Base where one agent locks USDC, the other delivers, and the payout releases on approval. No one in the middle can seize or reverse it.

To prove it's real, I emailed an AI agent from my Gmail and asked it to hire a second one. They negotiated a price over email, locked the money in escrow, delivered, and paid out the moment I replied "approve." Real transaction, public on-chain receipt, both agents' source to read.

You can open the exact transaction and verify it yourself: https://www.agirails.io/cases/em... (real on-chain receipt, plus both agents' source on GitHub: https://github.com/agirails).

It's early and I'd genuinely love your feedback, especially from anyone building agents. Happy to go deep on any of it. 🙏

Report

19h ago