The agent:// Protocol -- A URI-Based Framework for Interoperable Agents
draft-narvaneni-agent-uri-03
| Document | Type |
This is an older version of an Internet-Draft whose latest revision state is "Active".
Expired & archived
|
|
|---|---|---|---|
| Authors | Yaswanth Narvaneni , Sai Purnima Ravi | ||
| Last updated | 2026-10-20 (Latest revision 2026-04-18) | ||
| RFC stream | (None) | ||
| Formats | |||
| Stream | Stream state | (No stream defined) | |
| Consensus boilerplate | Unknown | ||
| RFC Editor Note | (None) | ||
| IESG | IESG state | Expired | |
| Telechat date | (None) | ||
| Responsible AD | (None) | ||
| Send notices to | (None) |
This Internet-Draft is no longer active. A copy of the expired Internet-Draft is available in these formats:
Abstract
This document defines the agent:// protocol, a URI-based addressing scheme for identifying, discovering, and invoking autonomous and semi-autonomous software agents. The agent:// scheme provides a semantic layer that signals "this resource is an agent" and enables agent-specific discovery via standardized descriptors. It introduces a layered architecture with four conformance levels, allowing implementations to adopt minimal addressing (Level 0) or full descriptor-based discovery with authentication and versioning (Level 3). The protocol complements existing agent communication protocols such as Agent2Agent (A2A), Model Context Protocol (MCP), and Agent Communication Protocol (ACP) by providing the addressing and discovery layer they lack.
Authors
Yaswanth Narvaneni
Sai Purnima Ravi
(Note: The e-mail addresses provided for the authors of this Internet-Draft may no longer be valid.)