google-agentic-commerce/a2a-x402

The A2A x402 Extension brings cryptocurrency payments to the Agent-to-Agent (A2A) protocol, enabling agents to monetize their services through on-chain payments. This extension revives the spirit of HTTP 402 "Payment Required" for the decentralized agent ecosystem.

What it solves

Before this extension, agents could communicate and perform tasks but had no built-in way to charge for the services they provide. The A2A x402 extension solves this by adding a layer of cryptocurrency payments to the agent-to-agent protocol, letting agents become commercial services that can accept payment on-chain.

How it works

The extension defines a simple three-step payment flow between agents:

  1. When a merchant agent requires payment for a service, it responds with a payment-required message.
  2. The client agent signs the payment details and sends them back in a payment-submitted message.
  3. The merchant verifies the payment, settles it on-chain, and replies with a payment-completed message, delivering the requested service.

The architecture separates the core protocol (data structures and functions for creating, signing, and verifying payments) from "executors" — middleware that automates the flow so developers can either build custom logic or use ready-made components.

Who it’s for

Developers building agent-based services who want to charge for their capabilities — such as API calls, data processing, or AI inference — without building payment infrastructure from scratch. The project includes language-specific implementations (e.g., Python, TypeScript) and examples to help get started.

Highlights

  • Brings HTTP 402 "Payment Required" spirit to the decentralized agent ecosystem.
  • Language-agnostic specification with libraries in multiple languages.
  • Functional core, imperative shell architecture for flexibility and ease of use.
  • Includes examples and a full specification in the repository.

Related

  • Project
    yzfly/Awesome-AGI-Agents

    A curated collection of articles, papers, frameworks, and platforms for building and researching AI agents, covering everything from introductory guides to cutting-edge projects and industry protocols.

  • Project
    SJTU-IPADS/SkVM

    SkVM is a compilation and runtime system that makes LLM agent skills portable and optimized across different models and agent harnesses.

  • Project
    joinly-ai/joinly

    A connector middleware that enables AI agents to join and participate in video calls on platforms like Zoom, Google Meet, and Microsoft Teams via voice and chat.

  • Project
    qntx/ovo

    ovo is a Rust library that lets you embed a multi‑agent runtime into your program. Agents can be spawned dynamically and controlled with Rhai scripts, while all actions are journaled for replay or debugging. It’s useful for building AI agents, automation pipelines, or any system that needs lightweight, scriptable concurrency. The crate is dual‑licensed (Apache‑2.0 or MIT) and maintained by the QuantX community.