Next.js-like framework building AI Agents that are payment-native. Bootstrap your agent with A2A, MCP, x402 payments, and ERC-8004 identity.
aixyz is a growing TypeScript project in the AI payments / x402 ecosystem, focused on ai, ai-agents, mcp, payment. It currently has 82 GitHub stars and 8 forks, and sits alongside related tools like nano-currency-mcp-server, ag402, froglet, awesome-agent-protocols, Agent402, magpie-x402.
Nextjs-like framework for bundling AI agents into deployable services with A2A, MCP, x402 payments, and ERC-8004 identity.
Documentation · Quick Start · How It Works · Examples · CLI · Protocols
Full documentation, API reference, and guides at aixyz.sh.
bunx create-aixyz-app my-agent
cd my-agent
bun run dev
Your agent is running. It exposes:
| Endpoint | Protocol | What it does |
|---|---|---|
/.well-known/agent-card.json |
A2A | Agent discovery card |
/agent |
A2A | JSON-RPC endpoint, x402 payment gate |
/mcp |
MCP | Tool sharing with MCP clients |
An aixyz agent has three parts: a config, an agent, and tools.
aixyz.config.ts declares your agent's identity and payment address:
import type { AixyzConfig } from "aixyz/config";
const config: AixyzConfig = {
name: "Weather Agent",
description: "Get current weather for any location worldwide.",
version: "0.1.0",
x402: {
payTo: "0x...",
network: "eip155:8453", // Base mainnet
},
};
export default config;
app/agent.ts defines your agent and its payment price:
import { openai } from "@ai-sdk/openai";
import { stepCountIs, ToolLoopAgent } from "ai";
import type { Accepts } from "aixyz/accepts";
import weather from "./tools/weather";
export const accepts: Accepts = {
scheme: "exact",
price: "$0.005",
};
export default new ToolLoopAgent({
model: openai("gpt-4o-mini"),
instructions: "You are a helpful weather assistant.",
tools: { weather },
stopWhen: stepCountIs(10),
});
Each file in app/tools/ exports a Vercel AI SDK tool and an optional accepts for MCP payment gating:
import { tool } from "ai";
import { z } from "zod";
import type { Accepts } from "aixyz/accepts";
export const accepts: Accepts = {
scheme: "exact",
price: "$0.0001",
};
export default tool({
description: "Get current weather conditions for a city.",
inputSchema: z.object({
location: z.string().describe("City name"),
}),
execute: async ({ location }) => {
// your logic here
},
});
That's it. Run bun run dev and aixyz auto-generates the server, wires up A2A + MCP + x402, and starts serving.
| Example | Description |
|---|---|
boilerplate |
Minimal starter (auto-generated server) |
chainlink |
Chainlink data feeds with custom server |
flight-search |
Flight search with Stripe payments |
local-llm |
Local LLM via Docker (no external API) |
with-custom-facilitator |
Bring-your-own x402 facilitator |
with-custom-server |
Custom server setup |
with-express |
Express middleware integration |
sub-agents |
Multiple A2A endpoints from one deployment |
with-tests |
Agent with test examples |
fake-llm |
Fully deterministic testing with fake() model |
with-vercel-blob |
MCP-only txt storage using Vercel Blob |
bun add aixyz # CLI included with the aixyz package
bunx aixyz --help # or run without installing
aixyz dev # Dev server with hot reload
aixyz build # Bundle for deployment (standalone, Vercel, or executable)
aixyz erc-8004 register # Register on-chain agent identity
aixyz erc-8004 update # Update agent metadata URI
See the CLI reference for all options.
A2A (Agent-to-Agent) — Agent discovery card + JSON-RPC endpoint. Other agents find yours and send tasks.
MCP (Model Context Protocol) — Expose tools to any MCP client (Claude Desktop, VS Code, Cursor).
x402 — HTTP 402 micropayments. Per-request payment with cryptographic proof, verified on-chain.
ERC-8004 — On-chain agent identity on Ethereum, Base, Polygon, Scroll, Monad, BSC, or Gnosis.
bun install # install dependencies
bun run build # build all packages
bun run test # run tests
bun run format # format with Prettier
PRs welcome. Please ensure bun run build && bun run test && bun run format pass before submitting.
MIT
Send Nano currency from AI agents/LLMs
Zero latency! Zero code change! Empower your AI agent with payment ability via x402 protocol! (Openclaw, Claude code, Cursor, Langchain, CrewAI, AutoGen...)
A protocol and node for a bot economy — bots create, publish, discover, buy, sell, and compose remote resources for value.
A curated list of protocols and standards for AI agents — MCP, A2A, ACP, AG-UI, AP2, x402, and 50+ more, organized by stack layer
500+ pay-per-call web tools + skill packs for AI agents — every one tested, priced, and settled on-chain. Paid in USDC over x402 on 8 chains, or free via proof-of-work on the pure-CPU tools. Self-hostable, MCP-native, deterministic. Plus the open x402 index (Find / Route / Leaderboard).
Collateral that can still sell itself — Magpie's x402 agent API: borrow SOL programmatically on Solana.
A local-first AI agent with persistent memory, emotional intelligence, and a peer-to-peer skills economy.
The trust layer for agent-to-agent commerce — natural-language mandates, ERC-7710 delegated permissions, x402 payments, escrow, and dispute resolution as one open, catch-all Agent Skill / Claude Code plugin.
Agent behavior that compiles
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.
Aser is a lightweight, self-assembling AI Agent frame.
Golang SDK for A2A Protocol