arvinlovegood/go-stock

🦄🦄🦄AI赋能股票分析:AI加持的股票分析/选股工具。股票行情获取,AI热点资讯分析,AI资金/财务分析,涨跌报警推送。支持A股,港股,美股。支持市场整体/个股情绪分析,AI辅助选股等。数据全部保留在本地。支持DeepSeek,OpenAI,...

View on GitHub ↗Jump to charts ↓

Summary Information

Updated 30 minutes ago
Added to GitGenius on September 8th, 2026
Created on December 17th, 2024
Open Issues & Pull Requests: 21 (+0)
GitHub issues: Enabled
Number of forks: 1,305
Total Stargazers: 7,495 (+0)
Total Subscribers: 46 (+0)

Repository Insights (GitGenius)

Most active contributors

Sign in to see contributor activity.

Related repositories by overlapping contributors

No overlapping-contributor repos identified yet.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Issue API getrepoissuespagesummary failed: 429 Rate limit exceeded. Please try again later.

Detailed Description

go-stock is an AI-powered stock analysis tool built in Go that integrates large language models to assist with investment research and decision-making.

The tool addresses the challenge of analyzing stock market data and identifying investment opportunities by combining real-time market data retrieval with AI-driven analysis. It fetches stock quotes, analyzes trending financial news, performs AI-assisted fund and financial analysis, and sends price movement alerts. The approach keeps all data local on the user's machine while supporting multiple LLM platforms including DeepSeek, OpenAI, Ollama, LMStudio, AnythingLLM, and several Chinese AI services. It covers Chinese A-shares, Hong Kong stocks, and US stocks, and can perform both market-wide and individual stock sentiment analysis.

The tool suits investors and traders who want to leverage AI for stock selection and analysis without relying on cloud-based solutions for data storage. It is particularly relevant for users in markets covering mainland China, Hong Kong, and the United States. The local-first data approach appeals to those concerned with privacy or who prefer to keep financial information on their own systems. The flexibility to choose from multiple LLM providers means users can select based on cost, availability, or model preference in their region.

The project shows active development with regular updates and maintains an engaged community through discussion channels. The codebase demonstrates ongoing refinement of features and integration with various AI platforms. The tool is distributed as a compiled application rather than requiring manual setup, indicating attention to user accessibility.