Self-hosted A-share quant workbench for building strategies, backtesting, live monitoring and AI-assisted analysis, with open API and MCP access.
ZhuLinsen/daily_stock_analysis
LLM-driven stock analysis system covering A-shares, HK, US, JP, KR and Taiwan stocks, pushing daily decision dashboards to chat apps and email.
- Stars
- 67,704
- Forks
- 55,976
- Open issues
- 44
- Last commit
- 7 hours ago
Repolode describes open-source projects and does not give investment advice. Trading and investing can lose money: assess the risk yourself and follow the laws where you live before using this project.
What is it?
This project runs daily analysis on a watchlist of stocks across A-shares, Hong Kong, US, Japanese, Korean and Taiwanese markets. It aggregates market quotes, K-line data, technical indicators, news and announcements, then uses an LLM to produce a decision report with scores, trend reads, buy and sell levels, risk alerts and catalysts.
Results can be pushed to WeCom, Feishu, Telegram, Discord, Slack or email. It ships with a web workbook for manual analysis, task progress, history reports, backtesting, portfolio tracking and configuration, plus an agent mode for multi-turn strategy questions. Free default data sources let it run without paid accounts, though the project notes free sources can be unstable.
Deployment options include GitHub Actions on a schedule, Docker, a local scheduler, or a FastAPI service. Output is for study and research and is not investment advice.
Key features
- 01Generates decision reports with scores, trend, buy/sell levels and risk alerts
- 02Covers A-shares, HK, US, JP, KR and Taiwan stocks plus ETFs
- 03Pushes results to WeCom, Feishu, Telegram, Discord, Slack and email
- 04Web workbench with manual analysis, history reports, backtesting and portfolio tracking
- 05Runs on GitHub Actions, Docker or a local scheduler
Use cases
- Getting a daily summary of a personal watchlist pushed to a chat app
- Running scheduled stock analysis without a server using GitHub Actions
- Testing how an LLM interprets market data and news for multiple markets
Quick start
- 1
Clone the repository
git clone https://github.com/ZhuLinsen/daily_stock_analysis.git && cd daily_stock_analysis - 2
Install dependencies
pip install -r requirements.txt - 3
Create the environment config file
cp .env.example .env && vim .env - 4
Run an analysis
python main.py
Things to know
- Needs at least one AI model API key, such as Modelflare, AIHubMix, Gemini, Anthropic or an OpenAI-compatible service.
- Free market data sources such as AkShare and YFinance are subject to rate limits and upstream changes, so stability is not guaranteed.
In collections
Topics
FAQ
- What is daily_stock_analysis?
- LLM-driven stock analysis system covering A-shares, HK, US, JP, KR and Taiwan stocks, pushing daily decision dashboards to chat apps and email. This project runs daily analysis on a watchlist of stocks across A-shares, Hong Kong, US, Japanese, Korean and Taiwanese markets. It aggregates market quotes, K-line data, technical indicators, news and announcements, then uses an LLM to produce a decision report with scores, trend reads, buy and sell levels, risk alerts and catalysts.
- Is daily_stock_analysis free to use? What license does it have?
- daily_stock_analysis is open source under the MIT license. Check the license terms before using it in commercial products.
- Is daily_stock_analysis still maintained?
- Actively maintained. The last commit to daily_stock_analysis was on Nov 7, 2026.
- What can I use daily_stock_analysis for?
- Getting a daily summary of a personal watchlist pushed to a chat app Running scheduled stock analysis without a server using GitHub Actions Testing how an LLM interprets market data and news for multiple markets
- How do I install daily_stock_analysis?
- Clone the repository: git clone https://github.com/ZhuLinsen/daily_stock_analysis.git && cd daily_stock_analysis Install dependencies: pip install -r requirements.txt Create the environment config file: cp .env.example .env && vim .env Run an analysis: python main.py
- Where can I get daily_stock_analysis?
- The source code and installation instructions are on GitHub: https://github.com/ZhuLinsen/daily_stock_analysis
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
A market environment and benchmark layer for financial reinforcement learning, providing market datasets and trading environments for developing and comparing DRL trading agents.
An open-source Python quant trading system for China A-shares covering data management, stock screening, timing, risk control and backtesting.
A-share (China stock market) AI research workstation for market analysis, theme tracking, stock research, portfolio inspection and post-market review, local-first desktop app.
An AI-assisted research workbench for A-shares, US and HK stocks, with watchlists, portfolio ledger, daily market review, stock deep-dives, backtesting and a local report library.
AI-assisted stock analysis desktop tool for A-shares, Hong Kong and US stocks, with local data storage and alerts, built on Wails and Vue.