HKUDS

Vibe-Trading

AI🌱 NEW PROJECT BOOST#LLM#Finance#Trading#Agents#Backtesting

// summary

Vibe-Trading is an AI-powered multi-agent workspace that translates natural language requests into executable trading strategies and portfolio analysis. It features 71 specialized finance skills and 29 pre-built swarm workflows to automate research, backtesting, and risk management across global markets. Users can easily export their generated strategies to platforms like TradingView, TDX, and MetaTrader 5 with a single command.

// technical analysis

Vibe-Trading is an AI-powered multi-agent finance workspace designed to bridge the gap between natural language intent and complex quantitative trading execution. By leveraging a swarm-based architecture, it orchestrates specialized agents to perform tasks ranging from strategy generation and cross-market backtesting to portfolio optimization and risk management. The project prioritizes developer experience and flexibility, offering a modular design that supports multiple LLM providers, diverse data sources, and seamless integration with existing trading platforms through standardized exports and MCP plugins.

// key highlights

Provides 29 pre-configured agent swarm presets that automate complex workflows like investment committee debates and global equity research.

Features 71 specialized finance skills that enable the agent to perform tasks from technical analysis and factor research to on-chain crypto data processing.

Supports cross-market backtesting across A-shares, HK/US equities, crypto, futures, and forex using 7 distinct engines with statistical validation.

Enables one-click strategy exports to industry-standard platforms including TradingView (Pine Script v6), TDX, and MetaTrader 5.

Implements persistent cross-session memory and context compression to ensure the agent evolves its capabilities and retains user preferences over time.

Offers a unified data interface that automatically handles fallbacks across 5 different sources, ensuring reliable market data access without manual configuration.

// use cases

Automated strategy generation and backtesting across global equities, crypto, and futures

Multi-agent swarm orchestration for complex investment, trading, and risk management workflows

Cross-market portfolio analysis and multi-platform strategy export to TradingView, TDX, and MT5

// getting started

To begin, install the package via 'pip install vibe-trading-ai' and run 'vibe-trading init' to configure your environment variables. You can then launch the interactive CLI with 'vibe-trading' or start the web interface using 'vibe-trading serve'. Alternatively, users can deploy via Docker or integrate the project as an MCP plugin for existing agentic workflows.