Skip to content
Get packs

daily_stock_analysis

LLM-driven stock analysis tool that gathers market data and news, then pushes daily reports to chat apps.

GitHub Download v3.33.0
Stars
67.4k
Forks
55.8k
Licence
MIT
Language
Python
Last update
4 days ago
Type
App

What it is

This is a Python system that analyzes a watchlist of stocks across several markets using a large language model (LLM). It pulls market data and news from multiple sources, produces a 'decision dashboard' with scores, trends, and risk notes, and can send the results to messaging apps such as WeChat Work, Feishu, Telegram, or email. The README says it can run on a schedule through GitHub Actions at no cost.

  • Run a daily scheduled analysis of your watchlist via GitHub Actions and receive the report in WeChat, Feishu, Telegram, or email
  • Run a one-off analysis of specific tickers from the command line with python main.py --stocks
  • Use the web workspace to run manual analyses, browse history reports, and run backtests
  • Import holdings from images, CSV, or Excel files

Great for

  • Individual investors who follow a personal watchlist of A-shares, HK, US, or other listed stocks and want a daily summary
  • Developers who want a self-hosted, scriptable stock analysis pipeline
  • People comfortable setting up API keys and GitHub Secrets
  • Users who want daily reports pushed to a chat app they already use

Not ideal for

  • Anyone looking for guaranteed or investment-grade trading advice: the output is LLM-generated and the README presents it as analysis, not a guarantee
  • Users who cannot obtain an LLM API key or run a local model, since an AI model is required
  • Users who need highly reliable real-time data: the README says free data sources are subject to rate limits and interface changes with no stability guarantee
Step-by-step guide: how to use daily_stock_analysisInstall, first run, examples, tips and FAQs
daily_stock_analysis alternativesdaily_stock_analysis vs FinGPTdaily_stock_analysis vs Qbot

How to get it

  1. 1

    Clone and build from source

    You'll need: Python 3.10+ · An LLM API key (for example Modelflare, AIHubMix, Gemini, or an OpenAI-compatible service) or a local Ollama model

    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 config file

    cp .env.example .env && vim .env

    Run analysis

    python main.py
  2. 2

    Run it

    • Set up a .env file with at least one LLM API key and a stock list (STOCK_LIST or the --stocks flag)
    • Run python main.py --dry-run to test the pipeline (the README lists this option; its exact behavior is in the full guide)
    • Run python main.py --stocks 600519,hk00700,AAPL,2330.TW to analyze specific stocks
    • Check the notification channel you configured for the report
  3. 3

    Get the most out of it

    • Add at least one news search key (such as SerpAPI or Anspire), which the README says significantly affects sentiment and catalyst quality
    • Configure a token-based market data source like Tushare for A-shares for more stable historical data
    • Use the GitHub Actions route for free scheduled runs; the default schedule is weekdays at 18:00 Beijing time
    • Try the --debug flag or the web workspace (python main.py --serve-only) to inspect results and history

Downloads

Source code (.zip)main branch · straight from GitHubRelease v3.33.06 files incl. latest.ymlOfficial website & docsdsa.zhulinsen.tech

Strengths

  • The README lists many market data sources and AI model options, and says it can run with free default data sources
  • Scheduled runs and notifications are documented, including a GitHub Actions path that needs no server
  • The project is MIT-licensed and has a large community (67,244 stars at time of metadata)

Trade-offs

  • The README notes that free data sources can be unstable and that stability is not guaranteed; paid or token-based sources are suggested for regular use
  • Setup involves several API keys and secrets, and the README points to a long external guide for full configuration
  • Much of the detailed behavior lives in separate docs; the README itself is truncated and summarizes many features

How it compares

ProjectStarsTypeLevelUpdatedBest for
daily_stock_analysis (this)67.4kAppintermediate4 days agoIndividual investors who follow a personal watchlist of A-shares, HK, US, or other listed stocks and want a daily summary
FinGPT21.5kAI model / agentadvanced11 days agoDevelopers who want to experiment with finance-tuned LLMs for sentiment analysis
qlib49.9kLibraryadvanced7 days agoQuant researchers who want a structured ML workflow for stock data
Qbot18.8kAppadvanced8 months agoPython users who want to research quantitative trading strategies
Vibe-Trading37.4kAI model / agentintermediate4 days agoDevelopers who want an AI agent for quantitative trading research
nanobot49.8kAppintermediate4 days agoPeople who want a self-hosted personal assistant they can inspect and customize

Stats synced from GitHub. The assessment above was drafted with AI from the project's README on 2026-10-29 and may miss recent changes — check the README before relying on a command. MIT licence: free to use, modify and distribute, including commercially, as long as you keep the copyright notice.