Ripple Labs, through RippleX, has launched the XRP Ledger AI Starter Kit, a set of developer tools designed to enable autonomous payments for AI agents on the XRP Ledger (XRPL).
The XRP Ledger AI Starter Kit launched on June 10 and is rolling out in stages. The first phase is expected to focus on helping developers build agent-powered applications on the XRPL network.
“The XRP Ledger was built with many of these qualities in mind, including fast settlement, low and predictable costs, and native payment functionality. As agentic payments move from experimentation to real-world adoption, those capabilities become increasingly important,” the announcement noted.
At the center of the launch is support for X402, an open protocol that lets software make payments over the web without human approval. Through a contribution from t54, an infrastructure startup Ripple backed in a seed round, the XRPL is now a supported chain on X402.
This allows AI agents to pay for services such as application programming interface (API) calls, model inference, and other digital services using XRP and Ripple USD (RLUSD). Beyond payments, the kit includes tooling for AI coding agents. Through a dedicated Model Context Protocol (MCP) server, clients such as Claude Code, Claude Desktop, and Cursor can now query XRPL documentation directly.
XRP Ledger prepares for AI Agentic payments
The XRP Ledger AI Starter Kit arrived the same day Mastercard Inc. (NYSE: MA) launched Agent Pay for Machines (AP4M), a framework for autonomous payments backed by more than 30 partners, including Ripple and t54. RippleX senior vice president Markus Infanger said XRPL and RLUSD give Mastercard’s framework a settlement layer that clears in seconds, with predictable costs, built-in compliance, and a full audit trail.
As such, XRP Ledger is well positioned to grow its on-chain activity, potentially fueling bullish sentiment for XRP. Furthermore, the XRPL has seen its adoption grow steadily over the past months, with its addresses hitting an all-time high, as Finbold reported.
