AI Stock Smart Review Tool

Kevin, former senior architect at major internet companies, now focused on AI projects like AI quantitative investment, AI overseas expansion, and helping enterprises/individuals with AI transformation.

Uses 4 professional Agents working together: Query handles data retrieval, Analyze handles trend analysis, Summary generates reports, Planner coordinates overall scheduling. Unlike single large models, each Agent focuses on its domain, collaborating on complex tasks. Tech stack: Python + OpenAgents + WebSocket + Kotlin + Jetpack Compose. Core features: Natural language queries ('Beijing stock exchange quotes'), real-time data analysis (7-day trends + sentiment), Markdown table rendering, WebSocket auto-reconnect, local chat history.

Multi-agent collaboration architecture - not one large model doing everything, but 4 specialized Agents: Query Agent (Query Expert) uses akshare for real-time index data; Analyze Agent (Analysis Expert) for sentiment analysis + trend recognition + index comparison; Summary Agent (Summary Expert) generates structured Markdown reports; Planner Agent (Coordinator) for intelligent routing + task orchestration. Modern tech stack - Backend: OpenAgents multi-agent framework, Python + WebSocket real-time communication, akshare stock data interface, Nginx reverse proxy. Frontend: Kotlin + Jetpack Compose declarative UI, MVVM architecture + Coroutines + Flow, WebSocket auto-reconnect (3 retries), complete Markdown rendering (tables/bold/lists).

Query Agent (Query Expert) uses akshare for real-time index data. Analyze Agent (Analysis Expert) for sentiment analysis + trend recognition + index comparison. Summary Agent (Summary Expert) generates structured Markdown reports. Planner Agent (Coordinator) for intelligent routing + task orchestration.