World extends AgentKit for verified AI agents using World ID. AI agents can act online on behalf of authenticated human users. This system aims to prevent bots while enabling reliable automation.
World is expanding access to AgentKit. AgentKit is a framework designed to help individuals create human-verified AI agents and connect those agents to verified World IDs.
This system allows AI agents to act on your behalf over the Internet while maintaining your identity across a global network.
This development comes as AI agents become increasingly capable of performing online tasks such as shopping, making reservations, navigating websites, and interacting with digital services.
This increased capability creates challenges for enterprises to distinguish between agents representing real users and automated bot networks.
AgentKit is positioned to address that problem by directly linking AI agents to World ID, allowing websites and applications to verify when an agent is acting on behalf of a unique human.
This framework is designed to support task delegation while maintaining safety measures associated with identity verification and user control.
How AgentKit links AI agents to verified identities
To start using AgentKit, you need an authenticated World ID, access to the World App, and a supported AI agent (including tools like Claude Code, Codex, Cursor, Hermes, and OpenClaw).
Users connect a human certificate through World’s ToolRouter interface, generate an API key, and link an AI agent within minutes.
Once connected, agents can interact with services that support AgentKit and perform tasks on your behalf.
The system is designed to allow individuals to delegate digital tasks to AI agents while maintaining the control associated with a verified identity.
According to the framework’s description, this structure is intended to ensure that AI activity is attributed to actual human users, rather than anonymous or automated systems.
Demo shows real-world usage examples
This technology was recently demonstrated through the limited edition release of 500 “Human in the Loop” hats, available only to verified World ID holders.
During the demonstration, an AI agent discovered drops, verified eligibility, navigated the storefront, and completed purchases on behalf of users while maintaining a limit of one item per person associated with a verified ID.
All 500 hats were owned by individuals identified in multiple countries, including the United States, Germany, Japan, and the United Kingdom.
This demonstration was used to show how an AI agent can perform real-world transactions while maintaining identity-based constraints designed to limit abuse.
This example highlighted how companies can enable AI agents to complete tasks on behalf of users while preventing abuse by bot networks.
Building a trust layer for the agent economy
As more services integrate AgentKit, World aims to create what it describes as a layer of trust for the emerging agent economy.
The goal is to enable AI agents to transact and interact online while being accountable to the humans they represent.
The system is intended to support an increasingly wide range of use cases in which AI agents operate autonomously, but within a framework of verified identity and user authentication.
This includes both commercial applications and broader digital service interactions.
The World project was originally conceived by Sam Altman, Max Novendstern, and Alex Blania and aims to provide evidence of humanity, economics, and connectivity for all humans in the age of AI.
The company says AgentKit is part of a broader effort to support identity verification in environments where AI agents are empowered to act independently across online platforms.
