World Expands AgentKit As Demand Grows For Human-Backed AI Agents | Metaverse Post

In Brief

World is expanding access to AgentKit, its framework for creating human-verified AI agents and allowing individuals to connect AI agents to a verified World ID and act on their behalf across the internet.

World is expanding access to AgentKit, its framework for creating human-verified AI agents and allowing individuals to connect AI agents to a verified World ID and act on their behalf across the internet.

As AI agents become increasingly capable of completing tasks such as shopping online, making reservations, navigating websites, and interacting with digital services, businesses face a growing challenge: determining whether an agent represents a real person or an automated bot network.

AgentKit addresses that problem by connecting AI agents to World ID, enabling websites and applications to verify when an agent is acting on behalf of a unique human. The framework allows individuals to delegate tasks to AI agents while maintaining identity-based safeguards and controls.

Getting started requires a verified World ID, World App, and a supported AI agent such as Claude Code, Codex, Cursor, Hermes, or OpenClaw. Users can connect their proof of human through World’s ToolRouter interface, generate an API key, and link their agent in minutes, allowing it to interact with services that support AgentKit.

The technology was recently demonstrated through a limited-edition release of 500 “Human in the Loop” hats available exclusively to verified World ID holders. During the demonstration, AI agents discovered the drop, verified eligibility, navigated the storefront, and completed purchases on behalf of users while maintaining one-item-per-person limits tied to verified identities.

All 500 hats were claimed by verified individuals across multiple countries, including the United States, Germany, Japan, and the United Kingdom. The demonstration showed how businesses can allow AI agents to perform tasks on behalf of users while helping prevent abuse from bot networks.

As more services integrate AgentKit, World aims to create a trust layer for the emerging agent economy, enabling AI agents to transact and interact online while remaining accountable to the humans they represent.