Hansisunstoppable

Hansisunstoppable / AAAgent

Public

基于 Agentic RAG的 A股智能分析工具

16
0
100% credibility
Found May 08, 2026 at 16 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

AAAgent is an open-source platform for analyzing Chinese A-share stocks, enabling precise financial report queries, real-time market data, and announcement searches through a smart agent workflow.

How It Works

1
🔍 Discover the stock helper

You find a free tool that analyzes Chinese stocks like Moutai, giving smart insights on earnings and prices.

2
💻 Set it up on your computer

Download and install it with a simple command, like adding a helpful app.

3
🔑 Connect the smart thinker

Add your private password to let it use an AI brain for deep analysis.

4
📊 Load example stock info

Bring in sample data for big companies so it's ready to go.

5
💬 Ask about a stock

Type a question like 'Moutai's latest revenue growth?' and watch it think step by step.

6
📈 See clear answers

Get the exact numbers, sources, and confidence level, with options for deeper checks.

🎉 Master your stocks

Now you easily get reliable insights on any A-share stock, saving hours of research.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 16 to 16 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 AAAgent?

AAAgent is a Python-based agentic RAG system for analyzing Chinese A-shares, pulling precise financial metrics from reports, real-time quotes, and announcements via a simple CLI. Query like "贵州茅台 2024Q3 revenue growth" and get zero-hallucination answers with citations, backed by agentic RAG architecture using LangGraph for workflows. It solves unreliable LLM outputs in finance by routing queries across five paths—financial tables, narratives, market data, news, or general—with cell-level math execution and fallback data sources.

Why is it gaining traction?

This agentic RAG GitHub repo stands out with hybrid retrieval (BM25 + vectors), parallel three-role auditing that self-corrects low-confidence answers, and progressive disclosure to cut token waste—L1 metadata first, full audit on demand. Developers dig the agentic GitHub workflows for production uptime (99%+ via AKShare fallbacks) and open source agentic RAG pipeline that beats plain RAG on precise queries, per its eval scripts showing high router accuracy.

Who should use this?

Quant traders scripting A-share screeners, fintech devs ingesting AKShare data into apps, or analysts querying earnings without Excel drudgery. Ideal for building agentic GitHub Copilot extensions or agent zeta tools focused on Chinese markets, not global setups.

Verdict

Early prototype at 16 stars and 1.0% credibility—docs are solid with CLI quickstarts and evals, but lacks broad tests and real-world scale. Worth forking for agentic RAG LangGraph experiments if you're in A-shares; skip for mission-critical prod.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.