Agent Settlement Extension (ASE) is an economic metadata layer that extends existing agent-to-agent (A2A) and Model Control Protocol (MCP) communication protocols with economic semantics. ASE provides standardized schemas, validation, and reference implementations to enable agents to express economic intents, settlements, audit bundles, and related metadata in interoperable ways.

ASE makes economic semantics first-class in agent messaging and provides machine-readable schemas and validators for settlement, audit, and delegation tokens. The extension offers lightweight reference code to integrate ASE with agent frameworks and includes standardized structures for cost attribution, delegation, and settlement events.

The protocol provides JSON Schema files describing ASE data structures including audit bundles, delegation tokens, and monetary amounts. It includes reference Python implementation with core models, validation, serialization, business logic, and integration adapters for frameworks like LangChain and AutoGPT.

ASE enables agents to exchange not just tasks, but economic intent, building the foundation for governed, auditable agent economies. It adds standardized structures for cost attribution, delegation, and settlement events to existing agent communication protocols.

ASE is designed for developers working with agent frameworks and is part of the Caracal project. The package includes test suites validating cross-framework compatibility and protocol behavior, with adapters demonstrating integration patterns with popular agent frameworks.