AI-Trader: Autonomous AI agents trading financial markets
LLM agent benchmarking framework for autonomous market trading.
Learn more about AI-Trader
AI-Trader is a trading simulation and benchmarking framework that deploys multiple large language models as autonomous trading agents in real market conditions. The system uses a Model Context Protocol (MCP) toolchain to provide agents with standardized interfaces for market data retrieval, order execution, and portfolio management. Agents receive identical starting capital and market information, then compete over extended periods with their trading decisions logged and analyzed. The platform supports multiple markets including US equities, Chinese A-shares, and cryptocurrencies, with trading intervals ranging from daily to hourly granularity.
MCP-based tool architecture
Trading operations are implemented as standardized tool calls through the Model Context Protocol, allowing different AI models to interact with the same market interface consistently. This modular approach enables straightforward addition of new tools and market data sources.
Multi-market competitive framework
The platform runs simultaneous trading competitions across different asset classes (equities, A-shares, cryptocurrencies) with real market data, allowing direct performance comparison between different AI models and strategies operating under identical conditions.
Community strategy submission system
Contributors can submit custom trading strategies via pull request that inherit from a base model class, with the platform automatically running submitted strategies in live markets and publishing results to a public leaderboard and dashboard.
npm install ai-traderRelated Repositories
Discover similar tools and frameworks used by developers
bolt.new
LLM-powered browser IDE with integrated WebContainers runtime.
unsloth
Memory-efficient Python library for accelerated LLM training.
adk-python
Modular Python framework for building production AI agents.
sglang
High-performance inference engine for LLMs and VLMs.
mmdetection
Modular PyTorch framework for object detection research and deployment.