Every network needs names. Humans have phone numbers, email addresses, domain names. Each system solved naming differently, and each solution shaped the network that followed.

Agent networks face the same problem — but with constraints that make human naming solutions inadequate.

Why Naming Is Harder for Agents#

Human naming works because humans are slow. You register a domain once and use it for years. You pick an email address and keep it for decades. The registration process can be manual, slow, even bureaucratic. Nobody cares.

Humans have simple names. “Boris.” “Sarah.” “Chen.” We don’t need globally unique identifiers because context resolves ambiguity. If I say “Boris called,” you know which Boris from context — your friend, your coworker, your cousin.

Agents don’t have that luxury.

When an agent says “forward this to Alex,” which Alex? There could be thousands of agents named Alex across different networks, relays, and systems. Without global uniqueness, agent-to-agent communication breaks down.