BTC USD 86,003.0 Gold USD 4,333.54
Time now: Jun 1, 12:00 AM

Binance launches Agent OS platform for AI trading applications

Binance launches Agent OS platform for AI trading applications​

Leonardo_Lightning_XL_An_image_without_PhotoReal_and_Alchemy_b_0.jpg


Investing.com -- Binance launched Agent OS on Thursday, a developer platform designed to connect AI applications to the exchange’s trading, market data, wallet, payment and blockchain capabilities across cryptocurrency and traditional markets.

The platform is part of Binance Intelligence, the exchange’s strategic initiative for AI-powered products. Agent OS provides AI builders, fintech developers and quantitative trading teams with tools to create applications and agents that interact with Binance’s financial infrastructure. The platform supports both pre-built integrations and custom AI agents.

Users can authorize agents to access market data, view account information and execute trading activities through supported AI tools, including ChatGPT, Claude Code, Codex and Cursor. Access is subject to permissions and limits configured by users. Each agent can be assigned to a dedicated subaccount to separate funds and trading activity.

"Binance Agent OS addresses the fragmentation developers face when building agentic finance applications across crypto and traditional markets," said Jeff Li, VP of Product at Binance. "It gives everyone from developers to quantitative traders the reliable data, low-latency infrastructure, and standardized interfaces they need to deploy AI-driven strategies."

Agent OS combines Binance APIs, Binance Wallet Agentic Hub, Binance x402 for programmable payments, Binance Skill Hub and newly introduced support for the Model Context Protocol (MCP). MCP is an open standard that allows compatible AI applications to connect to and use external tools.

User-configured permissions control what data and trading capabilities an AI agent can access. Binance can monitor trading activity and orders but cannot see the agent’s workflow or decision-making process, which operates within the user’s chosen AI application.

The initial MCP implementation allows compatible AI applications to access market data, view read-only account information and place trades. Users can assign an agent to a dedicated subaccount, configure permissions and revoke access at any time through the MCP server.

Agents can view balances, portfolio information and transaction history for designated subaccounts, plus balance and portfolio data for the user’s main account. They cannot access non-trading personal information, including email addresses or KYC data.

Binance monitors and applies controls to trading activity initiated through the platform. The agent’s external information sources and decision-making occur within the user’s selected AI application and remain invisible to Binance.

This article was generated with the support of AI and reviewed by an editor. For more information see our T&C.

 
Back
Top
Log in Register