展示HN：多智能体AI股票分析器 – 在韩国市场实现408%的回报率
嘿，HN！我构建了PRISM-INSIGHT，这是一个多智能体系统，13个专业的AI智能体协作分析韩国股票（KOSPI/KOSDAQ）。它是完全开源的，自2025年3月以来一直在实时运行。
<p>[它的功能]
该系统每天自动检测两次上涨的股票，生成分析师级别的报告，并执行交易策略。每个智能体专注于不同的领域——技术分析、交易流、财务、新闻、市场状况等。它们像一个真正的研究团队一样协同工作。
<p>[我为什么要构建这个]
我想看看GPT-4和GPT-5是否能够真正复制人类分析师的工作，但没有典型的单一智能体的限制。因此，我将工作分配给多个专业智能体进行协作。交易模拟已经运行了8个月，使用的是真实的韩国市场数据。
<p>[如何尝试]
加入实时的Telegram频道！
<a href="https://t.me/prism_insight_global_en" rel="nofollow">https://t.me/prism_insight_global_en</a>（获取每日提醒和报告）
<p>查看实时仪表板！
<a href="https://analysis.stocksimulation.kr" rel="nofollow">https://analysis.stocksimulation.kr</a>（所有交易、表现、AI推理）
<p>克隆并自己运行！
<a href="https://github.com/dragon1086/prism-insight" rel="nofollow">https://github.com/dragon1086/prism-insight</a>
<p>[有趣的部分]
该系统使用MCP（模型上下文协议）服务器，使智能体能够访问实时市场数据、网络搜索和金融API。我使用GPT-4.1进行分析，GPT-5进行交易决策，Claude Sonnet 4.5作为对话机器人。
<p>第一次交易模拟（第一季，2025年3月至9月）在51笔交易中获得了408%的回报。当前季（第二季）实现回报为+11%，而KOSPI为+16%。现在也在用真实资金运行（$10,000账户，自9月底以来上涨了9.35%）。
<p>[技术栈]
使用Python 3.10+，全程使用async/await，SQLite用于交易历史，Playwright用于PDF报告，matplotlib用于图表。整个系统大约有8400行Python代码，分布在56个文件中。
<p>[与众不同之处]
大多数AI交易项目要么是单一智能体，要么是黑箱。这一项目采用多智能体架构，您可以清楚地看到每个智能体正在分析什么以及为什么。所有内容都是透明的——仪表板显示每笔交易、每个决策和所有推理。
<p>它是MIT许可证的，如果您愿意，可以完全在您的机器上运行。我正在承担API费用（约$200/月），以保持公共Telegram频道对450多名用户（韩国频道+全球频道）的免费。
<p>欢迎对多智能体方法提供反馈或询问关于在生产中运行AI智能体的问题！
查看原文
Hey HN! I built PRISM-INSIGHT, a multi-agent system where 13 specialized AI agents collaborate to analyze Korean stocks (KOSPI/KOSDAQ). It's completely open source and has been running live since March 2025.<p>[What it does]
The system automatically detects surging stocks twice daily, generates analyst-level reports, and executes trading strategies. Each agent specializes in something different – technical analysis, trading flows, financials, news, market conditions, etc. They work together like a real research team.<p>[Why I built this]
I wanted to see if GPT-4 and GPT-5 could genuinely replicate what human analysts do, but without the typical single-agent limitations. So I split the work across multiple specialized agents that collaborate. The trading simulation has been running for 8 months now with real Korean market data.<p>[How to try it]<p>Join the live Telegram channel!
<a href="https://t.me/prism_insight_global_en" rel="nofollow">https://t.me/prism_insight_global_en</a> (gets daily alerts and reports)<p>Check the real-time dashboard!
<a href="https://analysis.stocksimulation.kr" rel="nofollow">https://analysis.stocksimulation.kr</a> (all trades, performance, AI reasoning)<p>Clone and run it yourself!
<a href="https://github.com/dragon1086/prism-insight" rel="nofollow">https://github.com/dragon1086/prism-insight</a><p>[The interesting parts]
The system uses MCP (Model Context Protocol) servers to give agents access to live market data, web search, and financial APIs. I'm using GPT-4.1 for analysis, GPT-5 for trading decisions, and Claude Sonnet 4.5 for the conversational bot.<p>The first trading simulation (Season 1, Mar-Sep 2025) returned 408% across 51 trades. Current season(2) is at +11% realized returns vs KOSPI's +16%. Also running it with real money now ($10k account, up 9.35% since late September).<p>[Tech stack]
Python 3.10+, async/await throughout, SQLite for trade history, Playwright for PDF reports, matplotlib for charts. The whole thing is about 8,400 lines of Python across 56 files.<p>[What makes it different]
Most AI trading projects are either single-agent or black boxes. This one uses a multi-agent architecture where you can see exactly what each agent is analyzing and why. Everything is transparent – the dashboard shows every trade, every decision, and all the reasoning.<p>It's MIT licensed and runs entirely on your machine if you want. I'm covering the API costs (~$200/month) to keep the public Telegram channel free for 450+ users(Korean channel + Global channel).<p>Would love feedback on the multi-agent approach or questions about running AI agents in production!