韭菜盘 (JCP AI) is an AI-driven, cross-platform desktop application designed to provide intelligent stock analysis and investment recommendations. It targets investors and users seeking sophisticated, AI-powered insights by leveraging multi-agent collaboration. The system aims to make investment decisions smarter through multi-dimensional analysis provided by specialized AI experts.

How It Works

This project utilizes the Wails v2 framework, integrating a Go backend with a React frontend to create a hybrid desktop application. It connects to multiple AI large models, such as OpenAI and Google Gemini, through a sophisticated multi-agent system. These agents, each with distinct expert roles (e.g., Technical Analyst, Fundamental Analyst), collaborate to analyze stocks from various perspectives. A key innovation is its intelligent memory system, which maintains separate long-term memory for each stock, allowing AI to recall historical discussions and critical conclusions, thereby enhancing analytical continuity and depth.

Quick Start & Requirements

• Primary Install/Run: wails dev for development, wails build for release.
• Prerequisites: Go 1.24+, Node.js 18+, Wails CLI v2. Installation commands for Wails CLI and dependency downloads (go mod download, npm install) are provided.
• Configuration: Requires API Keys for AI models (OpenAI/Gemini), configured via the application's settings and stored in data/config.json.
• Links: Project repository: https://github.com/run-bigpig/jcp

Highlighted Details

• Multi-Agent Collaboration: Features distinct AI expert agents (Technical, Fundamental, Sentiment, Risk) that work together.
• Intelligent Memory System: Provides stock-isolated long-term memory, key fact extraction, historical summarization, and automatic context compression.
• Real-time Data & News Aggregation: Integrates live market data, K-lines, order book depth, and aggregates hot topics from platforms like Baidu, Douyin, Bilibili, and Toutiao.
• MCP Extensibility: Supports the Model Context Protocol, enabling the addition of custom tools for enhanced functionality.

Maintenance & Community

The repository outlines standard contribution guidelines via Issues and Pull Requests. Specific community channels (e.g., Discord, Slack), notable contributors, sponsorships, or a public roadmap are not detailed in the provided README.

Licensing & Compatibility

The project is licensed under the MIT License. This permissive license generally allows for commercial use and integration within closed-source projects without significant restrictions.

Limitations & Caveats

Core functionality is dependent on the availability and cost of external AI model APIs (OpenAI, Gemini). Setup requires specific development environment versions (Go, Node.js, Wails CLI) and manual API key configuration. The accuracy and availability of aggregated news and hot topic data rely on third-party sources.