Numb94

基于 CrewAI 多智能体协作的 A 股智能分析与推荐系统 | Multi-agent A-share stock analyst built on CrewAI

19
4
85% credibility
Found May 20, 2026 at 19 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

A Chinese A-stock market analysis and recommendation system built using CrewAI multi-agent collaboration for learning and research purposes, featuring backtesting capabilities, a Flask/Vue3 web interface, and multiple specialized AI agents for stock evaluation.

Star Growth

See how this repo grew from 19 to 19 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 crewai-astock?

This is a multi-agent stock analysis system designed specifically for China's A-share market. Built in Python on CrewAI, it orchestrates six AI agents that collaborate to analyze stocks, generate buy/sell recommendations, and monitor positions in real-time. The system includes a web dashboard for managing portfolios, tracking performance, and receiving push notifications when opportunities or risks arise.

Why is it gaining traction?

The project stands out by automating the entire stock analysis workflow through agent collaboration. Rather than running single queries, it chains together market intelligence, technical screening, risk assessment, and investment decision-making into a unified pipeline. Its multi-user architecture with session isolation means each user gets independent schedulers and data storage. The built-in news monitoring with sentiment analysis gives it an edge over simpler screening tools.

Who should use this?

Quantitative traders focused on Chinese A-shares who want to experiment with AI-driven recommendations will find this valuable. Retail investors seeking systematic analysis without building everything from scratch could benefit. Developers exploring CrewAI multi-agent patterns for financial applications can use it as a reference architecture. This is not for passive investors or those needing production-ready trading systems.

Verdict

At 19 stars with limited documentation and test coverage, this is an experimental project in active development. The credibility score of 0.85% reflects its early maturity. Worth exploring as a proof-of-concept or learning resource, but do not deploy this directly for actual trading decisions without significant validation and risk controls.

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.