Clawdentity: Cryptographic Identity and Trust Protocol for AI Agent Communication
draft-ravikiran-clawdentity-protocol-00
| Document | Type |
Expired Internet-Draft
(individual)
Expired & archived
|
|
|---|---|---|---|
| Author | Ravi Kiran Vemula | ||
| Last updated | 2026-08-25 (Latest revision 2026-02-21) | ||
| RFC stream | (None) | ||
| Intended RFC status | (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This Internet-Draft is no longer active.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 specifies the Clawdentity protocol, a cryptographic identity and trust layer for AI agent-to-agent communication. Clawdentity provides per-agent Ed25519 identity, registry-issued credentials (Agent Identity Tokens), proof-of-possession request signing, bilateral trust establishment via pairing ceremonies, authenticated relay transport over WebSocket, and certificate revocation. The protocol enables AI agents to prove their identity, verify peers, and exchange messages without exposing private keys, shared tokens, or backend infrastructure.
Authors
(Note: The e-mail addresses provided for the authors of this Internet-Draft may no longer be valid.)