World has expanded access to AgentKit, a framework that has enabled verified users to connect AI agents to their digital identities and prove those agents represent real people rather than automated bot networks.
Summary
- World has expanded AgentKit, allowing AI agents to operate on behalf of verified human users through World ID.
- The framework supports AI tools such as Claude Code, Codex, Cursor, Hermes, and OpenClaw.
- A recent sale of 500 limited-edition hats demonstrated how verified AI agents can complete purchases while enforcing one-person limits.
According to World, the rollout comes as AI agents take on a growing number of online tasks, increasing demand for systems that can distinguish between software acting for a specific individual and large-scale automated operations.
The project, backed by OpenAI CEO Sam Altman, said AgentKit allows users to delegate actions to AI tools while keeping identity verification and user controls in place.
The release follows a period of increased attention for the project after major U.S. crypto trading platform Robinhood listed the World token, bringing additional visibility to the ecosystem.
Verified identities allow AI agents to act for users
Details published by World show that AgentKit links supported AI agents to a verified World ID, enabling websites and applications to confirm that an agent is acting on behalf of a unique human user. The company said the system is designed to help businesses enforce user-level rules and reduce abuse associated with automated accounts.
To access the framework, World stated that users need a verified World ID, a World App account, and a compatible AI agent. Supported options currently include Claude Code, Codex, Cursor, Hermes, and OpenClaw.
Through World’s ToolRouter interface, users can create credentials and authorize their agents to interact with supported services. According to the company, this process allows individuals to assign tasks to AI systems without giving up identity verification tied to their accounts.
Rather than relying solely on account credentials, the framework adds proof that an agent represents a verified person, which World said can help online services distinguish legitimate activity from coordinated bot behavior.
Demonstration shows AI agents completing purchases
To showcase the technology, World recently organized a limited-edition sale of 500 “Human in the Loop” hats. According to the company, AI agents handled the entire purchase process for participating users.
World said the agents discovered the product launch, checked eligibility requirements, navigated the online storefront, and completed transactions without direct user involvement during the purchase flow.
Identity checks remained active throughout the event. According to the World, World ID verification ensured that purchase limits were enforced on a one-person-per-item basis, preventing users from bypassing restrictions through multiple automated accounts.
The company reported that all 500 hats were claimed by verified users located in countries including the United States, Germany, Japan, and the United Kingdom. World said the event demonstrated how businesses can permit AI agents to perform online actions while maintaining controls intended to reduce bot-driven abuse and automated farming activity.
As AI-powered software takes on more responsibilities across digital platforms, World said AgentKit provides a way to connect those agents to verified human identities, allowing organizations to verify who is ultimately behind automated actions carried out online.
