Urgent.News

One page, thousands of outlets. See who else covered it.

Editions

AI

Build OpenClaw agents that transact with Amazon Bedrock AgentCore payments

Give an autonomous agent a wallet and spending guardrails so it can pay for paywalled APIs, MCP servers, and web content. This post connects OpenClaw to Amazon Bedrock AgentCore payments and the x402 protocol, using the aws-agents-pay plugin to make bounded, human-approved testnet payments.

This article describes how to build autonomous agents, called OpenClaw agents, that can make payments to services requiring HTTP 402 Payment Required responses. OpenClaw is an AI assistant developed by the OpenClaw Foundation, which integrates with Amazon Bedrock AgentCore to provide payment capabilities. The payment system uses wallet-provider integration and a bounded payment session, where a human provisions the wallet, creates the payment session, and sets spending limits.

The aws-agents-pay plugin for OpenClaw allows the model-facing runtime to initiate approved testnet payments without human intervention. The design keeps wallet-provider credentials and payment authority outside the model, while still allowing protected credential handling and deterministic limits. OpenClaw agents can interact with various payment providers, such as Coinbase or Stripe Privy, which offer stablecoin wallets that can be funded using fiat or a debit card.

The plugin checks spending limits, network, asset, recipient, and amount against the operator's policy before processing the payment.

Written by urgent.news from AWS Machine Learning's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at aws.amazon.com →

More in AI

QUASAR: How Saliency-Weighted Reconstruction Closes the Loss Floor Gap in LLM Quantization-Aware Training

QUASAR: How Saliency-Weighted Reconstruction Closes the Loss Floor Gap in LLM Quantization-Aware Training Quantization is one of the most practical tools in the LLM deployment toolkit.

  • QUASAR addresses loss floor gap in 2-bit/3-bit quantization of LLMs
  • Saliency-weighted reconstruction prioritizes accurate parameter reconstruction
  • QUASAR achieves up to 29% reduction in KL divergence at 2-bit quantization

More from Monday 17 August →