<2-3 sentences summarising what the project addresses and solves, the target audience, and the benefit.> This project provides an intelligent decision-making system for financial markets, distilling a former fund manager's investment framework. It targets technically savvy users by offering data analysis, strategy backtesting, stock screening, and LLM-powered insights, enabling structured, data-driven investment decisions.

How It Works

The system distills extensive investment knowledge into a dual-mode architecture (JNB for real data, websearch for LLM). It integrates Tushare for financial data, processes it using Python modules to calculate 60+ technical indicators and identify 30+ trading strategies, and performs backtesting. An LLM layer, adopting a "Z哥" persona, provides interactive analysis and decision support, returning structured JSON data via a CLI.

Quick Start & Requirements

Installation involves cloning the repository and installing dependencies via pip install -r requirements.txt. Key prerequisites include a Tushare Token and API URL for real-time data (DATA_MODE=jnb). Optional LLM API keys enable conversational features. Initial data synchronization is required. Detailed setup and usage guides are available in docs/USER_GUIDE.md.

Highlighted Details

• Integrates real-time financial data via Tushare (K-lines, indicators, money flow, financial reports).
• Offers 60+ technical indicators, 30+ trading strategies, intelligent stock screening (e.g., "蜈蚣图", "沙漏评分"), and strategy backtesting.
• Features an LLM role-playing layer ("Z哥") for interactive analysis and decision support, with four-intent routing.
• Includes performance optimizations like vectorized indicator calculations and batch data writes.

Maintenance & Community

Active development is indicated by a detailed version history (v3.1.1 down to v2.0.0). No explicit community links (Discord, Slack) or notable contributor information are provided in the README.

Licensing & Compatibility

The project is released under the MIT License, which is permissive for commercial use and integration into closed-source projects.

Limitations & Caveats

The system is explicitly stated as not providing investment advice; financial markets carry high risk, and historical frameworks may fail. A past performance example shows underperformance relative to market benchmarks, highlighting execution challenges. LLM features are optional and require configuration.