LLM 驱动的多市场股票智能分析系统：多源行情、实时新闻、决策看板与自动推送，支持零成本定时运行。 LLM-powered multi-market stock analysis system with multi-source market data, real-time news, decision dashboard, automated notifications, and cost-free scheduled runs.
56.4k
Stars
48.6k
Forks
73
Open issues
94
Contributors
AI Analysis
An LLM-powered daily stock analysis system supporting A-share, HK, US, Japan, Korea, and Taiwan markets, which aggregates multi-source market data, real-time news, and technical indicators to generate AI decision dashboards pushed to WeChat Work, Feishu, Telegram, Discord, Slack, or email. It best serves individual retail investors and quantitative hobbyists in Chinese-speaking markets who want automated daily stock research without infrastructure costs, leveraging GitHub Actions for free sch...
Inferred from signals mentioned in the README (tests, CI, type safety) — not a review of the actual code.
AI's overall editorial judgment — not an average of the bars above, can weigh other factors too.
LLM-powered daily stock analysis for A-share and multi-market investors, with free GitHub Actions scheduling
daily_stock_analysis is a Python system that uses large language models to generate daily AI-written analysis reports for user-defined stock watchlists spanning A-shares, Hong Kong, US, Japanese, and Korean markets. It aggregates market data, technical indicators, capital flow, and real-time news, then pushes a formatted 'decision dashboard' to messaging platforms like WeChat Work, Feishu, Telegram, Slack, Discord, or email. Its primary audience is Chinese retail investors and hobbyist quant traders who want automated, low-cost daily briefings without running a server. The zero-cost GitHub Actions deployment path is a deliberate design choice that lowers the barrier to entry substantially.
Created in January 2026, the project is less than six months old. It appears to have been built during the wave of LLM-integrated personal finance tools that emerged after accessible API costs dropped. No prior version history or predecessor project is documented in the README.
The project reached 47,085 stars with 42,400 forks as of late June 2026 — an extraordinary fork-to-star ratio suggesting many users actively deploy their own instances. Gaining 4,133 stars in the last 7 days alone indicates sustained viral spread, likely amplified by being ranked #1 Python Repository of the Day on Trendshift and featured on HelloGitHub. Chinese developer communities on Bilibili (a tutorial video is linked) and social platforms appear to be the primary growth channels. The 'zero-cost, fork-and-deploy' model is a strong amplifier of fork counts.
The fork count of 42,400 strongly implies widespread personal deployment via the GitHub Actions fork-and-run model. A Docker image is published (zhulinsen/daily_stock_analysis on Docker Hub). Sponsors are listed (Anspire, SerpAPI), indicating some commercial ecosystem engagement. The Bilibili tutorial video and HelloGitHub feature suggest real user adoption in Chinese retail investor communities. However, there is no documented evidence of enterprise production deployments, SLA guarantees, or institutional usage.
Likely a modular Python pipeline: data ingestion adapters (AkShare, Tushare, YFinance, etc.) feed a central aggregator, which passes structured market context to an LLM prompt layer. Output is formatted as Markdown reports and routed to notification adapters. A FastAPI web workbench appears to provide a UI layer for manual analysis, history browsing, and configuration. GitHub Actions workflows handle scheduled execution. Docker support is also documented. The system appears to use a multi-source fallback pattern for data and LLM providers.
A CI badge is present in the README pointing to a ci.yml workflow, suggesting automated tests exist, but test scope and coverage percentage are not documented in the README.
Last push was 2026-06-22, two days before the evaluation date — actively maintained. The README is detailed and multi-language (Simplified Chinese, English, Traditional Chinese), and references versioned documentation and changelogs. Sponsor integrations and frequent feature additions (15 built-in agent strategies, backtesting, sentiment API) suggest ongoing active development rather than a maintenance-only phase.
ADOPT IF: you are a retail investor or hobbyist wanting automated daily LLM-written stock summaries pushed to your phone or team chat with minimal setup cost, especially if your focus is Chinese A-shares or multi-market watchlists. AVOID IF: you need audited financial advice, backtested alpha strategies with statistical rigor, or a production trading system — this is a personal information aggregation tool, not a trading engine. MONITOR IF: you are building a commercial or institutional tool and want to track whether the project's architecture scales beyond personal use, or whether its LLM prompt quality and data source reliability are validated over time.
Independent dimensions
Mainstream potential
5/10
Technical importance
5/10
Adoption evidence
6/10
- Heavy dependency on third-party data sources (AkShare, Tushare, YFinance, etc.) means breakage risk when upstream APIs change terms, rate limits, or structure — this is a chronic issue in Chinese financial data tooling.
- LLM-generated 'decision dashboards' carry significant risk of being treated as financial advice by non-expert users; the project does not appear to include prominent disclaimers in the README about this.
- The extremely high fork-to-star ratio (90%+) means many forks may be running divergent, unpatched versions, making it difficult to assess the true active user base or security posture of deployed instances.
- Sponsor and referral link density in the README introduces a potential conflict of interest in which data sources and LLM providers are recommended or prioritized.
- Project is less than 6 months old; long-term maintenance continuity is unproven, and the codebase has not yet been through a full market cycle or extended community stress-test.
Likely to remain a popular personal-use tool in Chinese retail investor communities for 12–24 months. May struggle to evolve into a serious trading infrastructure project given its architecture and positioning, but could grow into a well-maintained hobbyist ecosystem if community contributions stay active.
Newsletter
Get analyses like this every Monday
Free weekly digest of the most interesting open-source discoveries.
Languages
No language breakdown available.
Information
- Website
- https://dsa.zhulinsen.tech
- Language
- Python
- License
- MIT
- Last updated
- 2d ago
- Created
- 6mo ago
- Analyzed with
- anthropic/claude-sonnet-4-6
Stars over time
No commit data available.
Contributors over time
Top 100 contributors only — repos with more will plateau at 100.
Open issues
No open issues — clean slate.
Open pull requests
No open pull requests.
Top contributors
Contributor data not available yet.
Recent releases
No releases published yet.
Similar repos
shy3130/tickflow-stock-panel
A self-hosted quantitative trading workbench for Chinese A-stock analysis,...
hsliuping/TradingAgents-CN
TradingAgents-CN is a Chinese-localized multi-agent LLM framework for financial...
simonlin1212/TradingAgents-astock
A specialized multi-agent investment research framework adapted from...
| Repository | Stars | Week Δ | Language | Score | Updated |
|---|---|---|---|---|---|
|
ZhuLinsen/daily_stock_analysis
this
|
56.4k | +2.6k | Python | 8/10 | 2d ago |
|
shy3130/tickflow-stock-panel
|
2k | — | TypeScript | 8/10 | 10h ago |
 oficcejo/aiagents-stock
|
1.6k | — | Python | 6/10 | 2w ago |
|
hsliuping/TradingAgents-CN
|
30k | — | Python | 6/10 | 3mo ago |
|
simonlin1212/TradingAgents-astock
|
1.8k | — | Python | 7/10 | 2w ago |
 ArvinLovegood/go-stock
|
6.8k | — | Go | 7/10 | 10h ago |
A more academically framed multi-agent trading framework with 28,883 stars. Likely targets developers building trading research pipelines rather than retail investors wanting daily push notifications. daily_stock_analysis is more deployment-ready out of the box for non-technical users.
Go-based stock tool with 6,506 stars, likely targeting desktop/local use cases. daily_stock_analysis offers broader LLM integration and multi-channel push notifications but requires Python environment or Docker.
Smaller project (1,528 stars) in a similar space. daily_stock_analysis has substantially more features, documentation, and community traction.
A narrower A-share adaptation of TradingAgents with 1,349 stars. daily_stock_analysis covers more markets and has more notification channel integrations.
Appears to be a data-focused utility (5,289 stars) rather than a full analysis system. Serves a different but complementary function to daily_stock_analysis.
