simonlin1212

simonlin1212 / astock-peg

Public

A股 PEG 估值分析工具 — 彼得·林奇 PEG 投资法本地化实践 | A-share PEG valuation tool with AI-powered analysis

18
4
75% credibility
Found May 18, 2026 at 18 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
TypeScript
AI Summary

astock-peg is a free web tool that helps everyday investors analyze Chinese A-share stocks using the PEG (Price/Earnings-to-Growth) ratio — a popular investment method popularized by Peter Lynch. Users can build a personal watchlist of stocks, see real-time prices and valuation metrics, and generate AI-powered investment analysis reports that explain whether a stock is undervalued or overvalued. The tool also lets users compare a stock's valuation against its industry peers and stay updated with the latest news. All data comes from free public sources, and the tool works entirely in the browser with no database needed.

How It Works

1
🔍 You discover the tool

You hear about a free tool that helps analyze Chinese stocks using professional investment formulas.

2
🌐 You open the website

The dashboard loads instantly with a clean interface showing your personalized stock watchlist.

3
➕ You add stocks to watch

Type in a 6-digit stock code or the company name, and the stock appears on your dashboard with live prices.

4
🤖 You get an AI investment report

With one click, the tool gathers financial data and an AI generates a detailed PEG analysis report explaining whether the stock is undervalued or overvalued.

5
You explore different views
🏭
Compare with industry

See how your stock's valuation stacks up against the top 20 companies in its sector.

📰
Read latest news

Catch up on stock-specific news and market headlines all in one place.

6
📱 You save or share findings

Export your analysis report as a PDF to keep for your records or share with others.

✅ You invest with more confidence

You now have a clear picture of whether a stock is cheap or expensive relative to its growth, backed by professional analysis.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 18 to 18 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is astock-peg?

A PEG valuation analysis tool for China A-shares that implements Peter Lynch's investment methodology. It pulls real-time stock data from Tencent Finance, calculates PEG ratios, and generates AI-powered valuation reports. Built with Next.js and TypeScript on the frontend, with Python scripts handling financial data collection from public APIs like akshare and mootdx. Users enter a 6-digit stock code and get a structured analysis covering PE comparison, growth rates, and sector benchmarks in under 30 seconds.

Why is it gaining traction?

The tool solves a real pain point for retail investors: manually gathering financial data, calculating growth rates, and comparing against peers takes hours per stock. This automates the entire workflow. The AI report generation is the hook -- it produces a 7-section markdown analysis with PEG ratings, digestion timelines, and peer comparisons. The zero-database architecture means no setup friction; just clone, configure an API key, and run. Data comes from free public sources, which lowers the barrier to entry significantly.

Who should use this?

Individual investors in China A-shares who want a systematic approach to valuation without paying for Bloomberg or Wind terminals. Quantitative finance students learning PEG analysis will find the methodology transparent. Developers building investment dashboards could use this as a backend for the data collection layer. Not suitable for professional traders requiring real-time order execution or institutional-grade data feeds.

Verdict

A useful prototype for personal investment research with a clean interface and solid data sourcing strategy. The credibility score of 0.75% reflects the project's early stage -- 18 stars, limited documentation, and no visible test coverage. Use it for learning and personal analysis, but do not deploy in production without adding error handling and data validation. The architecture is sound; the project needs community contributions to mature.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.