Skip to content
/ AAIP Public

AI Agent Identification Protocol (AAIP) – A proposed standard for AI agents to transparently identify themselves across HTTP, gRPC, WebSocket, and MCP. Enables traffic management, analytics, and interoperability in the emerging Internet of AI Agents.

License

Notifications You must be signed in to change notification settings

j-mchugh/AAIP

Repository files navigation

AI Agent Identification Protocol (AAIP)

A transport-agnostic standard for AI agents to identify themselves when interacting with services.

Overview

Not all AI agents make network requests—some operate locally or use proprietary protocols. However, an increasing number of agents interact with external services—whether fully autonomously, semi-autonomously, or under human direction.

When AI agents do interact with external services, there's no standardized way for them to identify themselves. AAIP fills this gap with a canonical identity format that works across HTTP, gRPC, WebSocket, MCP, and SDK-level integrations.

Identity Format

<vendor>/<model> (<application>; <version>) [aid=<agent-id>]

Quick Example

AI-Agent: OpenAI/GPT-5.2 (MyApp; 1.2.0) [aid=atlas-prod]
Component Value Required
Vendor OpenAI
Model GPT-5.2
Application MyApp
Version 1.2.0
Agent ID abc123

Documentation

Document Description
SPECIFICATION.md Core protocol specification
BINDINGS.md HTTP, gRPC, WebSocket, MCP, SDK bindings
VERIFICATION.md Signed headers, JWT, mTLS verification
FAQ.md Common questions answered
USAGE_GUIDE.md Developer implementation guide
SAMPLES.md Example identity strings
SDK_INTEGRATION.md Framework integration guides

Quick Start

HTTP:

headers = {
    "AI-Agent": "OpenAI/GPT-5.2 (MyApp; 1.0) [aid=atlas-prod]"
}
response = requests.get("https://example.com", headers=headers)

gRPC:

metadata = [('x-ai-agent', 'OpenAI/GPT-5.2 (MyApp; 1.0) [aid=atlas-prod]')]
response = stub.MyMethod(request, metadata=metadata)

Key Features (v2)

Feature Description
Transport-Agnostic Same format for HTTP, gRPC, WebSocket, MCP
Identity + Capabilities Separate layers for different disclosure needs
Stable Agent ID aid= for analytics and allowlists
Verification Optional cryptographic authenticity
Delegation Support for multi-agent orchestration

Why AAIP?

  • Transparency: Servers can distinguish AI traffic from human traffic
  • Traffic Management: Rate limits and policies per agent
  • Analytics: Track AI usage patterns with stable IDs
  • Security: Verify agent identity when needed
  • Interoperability: Common format across protocols

Important Notes

⚠️ Self-Reporting: Core AAIP is self-reported and can be spoofed. Use verification extensions when trust is required.

Contributing

This is a proposed standard. Feedback and contributions welcome via GitHub issues.

License

MIT


Toward an Internet of AI Agents (IoA) with transparent, interoperable identity.

About

AI Agent Identification Protocol (AAIP) – A proposed standard for AI agents to transparently identify themselves across HTTP, gRPC, WebSocket, and MCP. Enables traffic management, analytics, and interoperability in the emerging Internet of AI Agents.

Topics

Resources

License

Stars

Watchers

Forks