daily_stock_analysis — What is it?

ZhuLinsen/daily_stock_analysis is an LLM-powered stock analysis system for A/H/US markets, providing automated analysis and multi-channel notifications.

⭐ 56,778 Stars 🍴 48,856 Forks Python MIT Author: ZhuLinsen
Source: README View on GitHub →

Why it matters

The project is gaining attention due to its integration of AI-driven analysis, multi-source data aggregation, and real-time news, offering a comprehensive solution for stock analysis. Its unique technical choices, such as support for various AI models and multiple notification channels, stand out.

Source: Synthesis of README and project traits

Core Features

AI Decision Reports

Generates detailed analysis reports with core conclusions, ratings, trends, trading points, risk alerts, catalysts, and operational checklists.

Source: README
Multi-Market Data Aggregation

Aggregates data from A-share, Hong Kong stocks, US stocks, and ETFs, including market data, K-line charts, technical indicators, fund flow, holding patterns, news, announcements, and fundamentals.

Source: README
Web/Desktop Dashboard

Features manual analysis, task progress tracking, historical reports, full Markdown reports, backtesting, portfolio management, configuration management, and light/dark theme options.

Source: README
Agent Strategy Questioning

Supports multi-round questioning and 15 built-in strategies, covering Web/Bot/API, including moving averages,缠论, wave theory, trend, hot topics, events, growth, and expectations.

Source: README
Automated Import and Completion

Supports image, CSV/Excel, and clipboard import, as well as stock code/name/pinyin/alias completion.

Source: README
Automation and Notifications

Supports GitHub Actions, Docker, local scheduled tasks, and notifications via WeChat, Feishu, Telegram, Discord, Slack, and email.

Source: README

Architecture

The architecture inferred from the code structure and dependencies suggests a modular design with clear separation of concerns. Key technical decisions include the use of ORM for database operations, scheduled tasks for automation, and integration with various AI models and data sources.

Source: Code tree + dependency files

Project Knowledge Graph

Knowledge graph: project (center) + core features (inner hexagons) + key dependencies (outer chips) python-dotenv tenacity sqlalchemy schedule exchange-calendarsexchange-calen… AI Decision Reports Multi-Market Data AggregationMulti-Market Data A… Web/Desktop DashboardWeb/Desktop Dashboa… Agent Strategy QuestioningAgent Strategy Ques… Automated Import and CompletionAutomated Import an… Automation and NotificationsAutomation and Noti… daily_stock_analysis Project Core feature Key dependency

Center: project; inner ring: core feature modules; outer ring: key dependencies. Auto-generated from core_features and tech_stack.key_deps.

Tech Stack

LanguagePythonFrameworkFastAPI for web services, SQLAlchemy for ORM, and schedule for task scheduling.
python-dotenvtenacitysqlalchemyscheduleexchange-calendarsefinanceaksharetusharepytdxbaostockyfinancelongbridgelark-oapipandaspypinyinopenpyxlnumpyjson-repairlitellmtiktokenopenaiPyYAMLtavily-pythongoogle-search-resultsrequestsmarkdown2imgkitfake-useragenthttpx
Docker, GitHub Actions, and local execution.
Source: Dependency files + code tree

Quick Start

git clone https://github.com/ZhuLinsen/daily_stock_analysis.git && cd daily_stock_analysis pip install -r requirements.txt cp .env.example .env && vim .env python main.py
Source: README Installation/Quick Start

Use Cases

The project is suitable for individual investors, financial analysts, and institutional investors who need automated stock analysis and multi-channel notifications. It is useful in scenarios such as daily market analysis, portfolio management, and investment decision-making.

Source: README

Strengths & Limitations

Strengths

  • Strength 1: Comprehensive stock analysis capabilities with AI-driven insights.
  • Strength 2: Support for multiple data sources and real-time news integration.
  • Strength 3: Flexible deployment options with Docker and GitHub Actions.

Limitations

  • Limitation 1: The project is still under active development and may have some bugs or limitations.
  • Limitation 2: The project requires some technical knowledge to set up and configure.
Source: Synthesis of README, code structure and dependencies

Latest Release

v3.17.1 (2026-05-16): Added Alert API MVP, supporting alert rule CRUD, enable/disable, one-time test, and trigger/notification result query. The first version covers 'price_cross', 'price_change_percent', and 'volume_spike', while maintaining legacy configuration compatibility and response desensitization.

Source: GitHub Releases

Verdict

ZhuLinsen/daily_stock_analysis is a promising project for those interested in automated stock analysis and AI-driven insights. It is particularly suitable for individuals and institutions looking for a comprehensive solution to manage their portfolios and make informed investment decisions.

Frequently Asked Questions

What is daily_stock_analysis?

ZhuLinsen/daily_stock_analysis is an LLM-powered stock analysis system for A/H/US markets, providing automated analysis and multi-channel notifications.

What are the main features of daily_stock_analysis?

daily_stock_analysis's core features include: AI Decision Reports, Multi-Market Data Aggregation, Web/Desktop Dashboard, Agent Strategy Questioning, Automated Import and Completion.

Why is daily_stock_analysis trending?

The project is gaining attention due to its integration of AI-driven analysis, multi-source data aggregation, and real-time news, offering a comprehensive solution for stock analysis.

What is daily_stock_analysis used for?

The project is suitable for individual investors, financial analysts, and institutional investors who need automated stock analysis and multi-channel notifications.

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: 2026-05-24 23:37. Quality score: 85/100.

Data sources: README, GitHub API, dependency files