daily_stock_analysis — What is it?

ZhuLinsen/daily_stock_analysis is an LLM-powered stock analysis system for A/H/US markets, providing multi-source data, real-time news, decision dashboards, and multi-channel notifications.

⭐ 35,694 Stars 🍴 35,188 Forks Python MIT Author: ZhuLinsen
Source: README View on GitHub →

Why it matters

The project is gaining attention due to its comprehensive stock analysis capabilities, integration of AI and LLM technologies, and ease of deployment through GitHub Actions and Docker. Its unique feature set, including multi-dimensional analysis, global market support, and automated notifications, addresses the pain points of manual stock analysis and decision-making.

Source: Synthesis of README and project traits

Core Features

AI Decision Dashboard

The system provides a decision dashboard with core conclusions, ratings, buy/sell points, risk alerts, and operational checklists, powered by AI and LLMs.

Source: README
Multi-dimensional Analysis

The system offers technical analysis, real-time market data, chart patterns, news sentiment, corporate announcements, and fundamental analysis aggregation.

Source: README
Global Market Support

Supports A-share, HK-share, US-share, US index, and common ETFs, providing a comprehensive view of global markets.

Source: README
Market Strategy System

Built-in strategies such as A-share review, US Regime, moving average,缠论,波浪理论, and sentiment cycle analysis.

Source: README
Automated Notifications

Supports notifications via WeChat, Feishu, Telegram, Discord, Slack, and email, with automated scheduling and multi-channel support.

Source: README

Architecture

The architecture is modular, with clear separation of concerns. Key modules include AI analysis, data processing, market analysis, and notification systems. The system uses a combination of design patterns like MVC for the web interface and dependency injection for the backend. Data flows through a series of interconnected modules, with a focus on scalability and maintainability.

Source: Code tree + dependency files

Tech Stack

infra: Docker, GitHub Actions, and local environments.  |  key_deps: python-dotenv, tenacity, sqlalchemy, schedule, exchange-calendars, efinance, akshare, tushare, pytdx, baostock, yfinance, longbridge, lark-oapi, pandas, pypinyin, openpyxl, numpy, json-repair, litellm, tiktoken, openai, PyYAML, tavily-python, google-search-results, requests, markdown2, imgkit, fake-useragent, httpx  |  language: Python  |  framework: FastAPI for web services, SQLAlchemy for ORM, Pandas for data analysis, and Litellm for LLM integration.

Source: Dependency files + code tree

Quick Start

Clone the repository, install dependencies with pip, configure environment variables, and run the analysis with `python main.py`. Alternatively, use GitHub Actions or Docker for deployment.
Source: README Installation/Quick Start

Use Cases

The project is suitable for individual investors, financial analysts, and institutional investors who need automated stock analysis, market strategy, and real-time notifications. It is useful for daily market analysis, long-term investment planning, and risk management.

Source: README

Strengths & Limitations

Strengths

  • Strengths: Comprehensive stock analysis capabilities, integration of AI and LLM technologies, ease of deployment, multi-channel notifications, and support for global markets.

Limitations

  • Limitations: May require technical expertise to set up and configure, and the effectiveness of AI-driven analysis depends on the quality of the data and models used.
Source: Synthesis of README, code structure and dependencies

Latest Release

v3.15.0 (2026-05-05): Added Anspire OpenAI-compatible gateway integration, improved market review, and other enhancements.

Source: GitHub Releases

Verdict

ZhuLinsen/daily_stock_analysis is a valuable tool for investors and analysts looking for an automated, AI-powered stock analysis system. Its comprehensive feature set, ease of deployment, and support for global markets make it a strong candidate for those seeking to enhance their investment decision-making process.

Transparency Notice
This page is auto-generated by AI (a large language model) from the following public materials: GitHub README, code tree, dependency files and release notes. Analyzed at: 2026-05-09 06:34. Quality score: 85/100.

Data sources: README, GitHub API, dependency files