Binance Lets AI Agents Trade Crypto For Users

By Boluwatife Kehinde-Idowu

Binance has launched a new platform that allows artificial intelligence agents to analyse cryptocurrency markets and execute trades on behalf of users, bringing autonomous AI into real-money financial transactions.

According to TechCrunch, Binance unveiled the platform, called Agent OS, on Thursday, allowing developers to connect AI applications and agents directly to the exchange’s financial infrastructure.

Agent OS brings together Binance’s existing tools, including its APIs, Wallet Agentic Hub, x402 transaction verification and payment facilitator API, as well as its Skill Hub. The platform also supports the Model Context Protocol, or MCP, which allows AI applications to connect with external tools and services.

The system can work with AI tools including OpenAI’s ChatGPT and Codex, Anthropic’s Claude Code and Cursor. Once authorised by users, the agents can access market information, view account details and execute cryptocurrency trades.

However, Binance is placing much of the responsibility for controlling the AI agents on users. They decide what an agent can access, what type of transactions it can perform and how much money it can use.

Jeff Li, Binance’s vice president of product, said the company was giving users detailed control over the actions their AI agents could perform.

“Instead of total freedom, we put the power in users’ hands to give them the granular access control of what they can do through the agent,” Li told TechCrunch.

Binance uses dedicated sub-accounts as one of its main safeguards. Users can assign a sub-account to an AI agent and limit its activities to specific functions such as spot or futures trading.

Withdrawals from those accounts are blocked by default, creating a separate financial environment for the AI agent.

Users can also choose whether an agent must receive approval before every trade or whether it can execute transactions independently after its permissions have been configured.

Binance does not impose a separate limit on how much an AI agent can trade or lose through a sub-account. Instead, the amount of money transferred into the account effectively determines the funds available to the agent.

There is also a potential blind spot: Binance cannot see the reasoning behind an AI agent’s trading decisions.

Read Also: Federal High Court To Hear Case Against Binance September 2

Li said the reasoning takes place outside Binance’s systems, either on the user’s computer or within the AI application they have selected.

This means Binance can monitor the trades an agent makes but has limited visibility into whether a decision was based on faulty information, manipulation, or a malicious prompt.

The issue is particularly important as AI agents become more capable of acting independently. A compromised agent or a successful prompt-injection attack could potentially influence the actions it takes.

Binance said its existing security, risk-control and anti-money-laundering measures for sub-account APIs would apply to Agent OS.

Trading is only one of the uses Binance has in mind. The company said AI agents could also monitor markets, conduct research, analyse risk, respond to market signals and execute strategies such as arbitrage.

Agent OS also gives AI agents access to payments and blockchain activity. Through Binance’s x402 integration, agents can send and settle payments, while the company’s Agentic Wallet allows them to interact with tokens and decentralised finance protocols.

Binance has introduced daily limits for Agentic Wallet transactions. Regular swaps are capped at $50,000 per day, while DeFi transactions have a default limit of $100,000. Payments through x402 are limited to $20 per day.

Li described Agent OS as Binance’s “first step” towards allowing developers to build AI-powered applications capable of operating across cryptocurrency and traditional financial markets.

Binance is not the only cryptocurrency exchange moving towards agentic trading.

Kraken has introduced an open-source command-line tool with an MCP server that allows AI agents to carry out actions including spot and futures trades.

Coinbase has also launched Coinbase for Agents, enabling AI agents to access user accounts and perform functions such as trading and payments within user-defined limits.

OKX has similarly introduced an MCP toolkit designed to support AI-powered trading.

The development marks a significant shift in the role of AI in finance. Instead of simply providing users with market information or answering questions, AI agents are increasingly being given the ability to take financial actions themselves.

For users, that could mean faster and more automated trading. But it also puts greater emphasis on security, permissions, and risk management, as an AI agent with access to real money can make decisions and execute transactions without human approval.