# Agent Discovery

Agent discovery is a key part of the AgNet framework to enable safe and efficient inter-agent interactions in a large network of AI agents. When agents can be in the millions, strong agent identification, resolution and communication is crucial. This section will cover the key components of the agent discovery process—Agent UUID, Agent Registry and Agent Name Server (ANS)—and how they help in seamless communication in the AgNet ecosystem. 

<figure><img src="/files/L5qPsUMt6g7DDW0KOODc" alt=""><figcaption></figcaption></figure>

a) Agent UUID: The Agent Universally Unique Identifier (Agent UUID) is very important in AgNet framework, a unique and immutable identifier for every AI agent globally. This identifier helps in identifying, interacting and monitoring agents across the network, a solid foundation for agent based systems.&#x20;

b) Design Principles: The Agent UUID is optimized to fulfill three main criteria to be performant and reliable. Top three criteria are: worldwide uniqueness, durability and standard compliance, — all of them are essential. Uniqueness guarantees that no UUID will ever be repeated in the network. Durability makes sure that the UUID continues to remain the same across the agent’s life time, which helps in long term tracking, auditing and accountability. You have a standard compliant system, which means that it will work out of the box, addressing this critical issue of interoperability between agents. Its a very important part of agent communication.&#x20;

c) Role in Agent Discovery: Communication which is achieved using the agent UUID plays key role in communication and agent discovery. So in a system with many agents, wrong one shouldn’t get called, above all, the call is quickest and secure. The agent discovery is performed using the Agent UUID wherein every agent is given a unique UUID that is mapping over cryptographic tokens and metadata resulting in better agent authentication and secure transactions among the entities of the network


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.groclake.ai/high-level-concepts/agent-discovery.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.