Korbit Unveils AI Agent Trading Support for ChatGPT and Claude

Korbit, a South Korean cryptocurrency exchange, has unveiled an AI agent trading environment that uses generative AI tools such as ChatGPT and Claude for tasks ranging from price checks to order execution.

Korbit said July 24 that it had launched Korbit CLI, an installable Command Line Interface program. The tool runs on a user's PC and connects with AI agents such as ChatGPT Codex and Claude Code, letting users access exchange functions including price inquiries, balance checks, orders, and deposits and withdrawals through natural-language commands.

Korbit CLI includes a Model Context Protocol server and AI agent skills. It was designed so AI agents can understand and use Korbit's functions and carry out tasks based on user requests without requiring a separate development environment.

The exchange also offers a paper-trading environment for testing AI-based automated trading programs without using real assets. Developers can test orders, executions and balance changes in the same environment as Korbit's open API to verify how their programs perform.

Korbit is also providing Korbit TUI, or Text-based User Interface, for developers who prefer working in a terminal environment. Users can view real-time prices, order books and candlestick charts on the terminal screen and use key functions including orders and deposits and withdrawals.

The company also published an AI-friendly document called llms.txt to make its open API documentation easier for AI systems to understand. Developers can provide the file to AI coding agents to build tools such as price collection programs and trading bots more efficiently.

Lee Jung-woo, Korbit's chief technology officer, said that when AI handles real assets, execution reliability, traceability and a robust pre-validation system matter alongside model performance. Korbit has built a foundation for AI to use the exchange's functions more accurately and safely through its Model Context Protocol server, agent skills, paper-trading environment and llms.txt, he added.

The company plans to continue expanding infrastructure that allows AI agents to connect directly and trade digital assets.