Claude-Code-Stock-Deep-Research-Agent  by liangdabiao

AI-powered deep research system for financial and general topics

Created 3 months ago
268 stars

Top 95.6% on SourcePulse

GitHubView on GitHub
Project Summary

Summary

This repository offers an automated, 8-phase stock investment due diligence system powered by Claude Code. It targets investors and researchers by deploying ~28 parallel agents to conduct deep, data-driven analysis of publicly traded companies globally, culminating in a comprehensive due diligence report.

How It Works

The system utilizes an 8-phase due diligence framework, integrating WebSearch, WebFetch, and comprehensive analysis tools. Its core innovation lies in the parallel execution of ~28 research agents, adapting research strategies to specific investment styles (value, growth, turnaround, dividend). Quality assurance is paramount, featuring mandatory cross-validation (e.g., profit vs. cash flow, company vs. peers) and citation verification with source quality ratings (A-E).

Quick Start & Requirements

  • Primary Command: Execute within Claude Code: /stock-research [ticker] (e.g., /stock-research AAPL).
  • Prerequisites: Requires Claude Code environment. Model Opus is recommended.
  • Estimated Setup: Standard due diligence reports take 2-4 hours to generate.
  • Documentation: README serves as primary documentation.

Highlighted Details

  • Comprehensive Analysis: Covers business models, industry dynamics, financial quality, governance, and valuation.
  • Multi-Agent Execution: Employs ~28 concurrent agents for efficient research.
  • Investment Style Adaptation: Tailors analysis for value, growth, turnaround, or dividend investing strategies.
  • Valuation Methods: Incorporates DCF, reverse DCF, relative valuation, and scenario analysis.
  • Risk Management: Includes detailed bear case analysis and monitoring checklists.
  • Research Coverage: Supports A-shares, Hong Kong, US, and other global stock markets.
  • Structured Output: Generates a standardized 20-file due diligence report with a fundamental-based signal rating (🟢🟢🟢/🟡🟡🟡/🔴🔴).

Maintenance & Community

Developed by Ankit at My Business Care Team (MyBCAT). The "Stock Research Edition" is dated December 2025. No specific community channels or roadmap details are provided in the README.

Licensing & Compatibility

Licensed under the permissive MIT License, allowing for broad use, including commercial applications and linking within closed-source projects.

Limitations & Caveats

This system explicitly disclaims providing investment advice or stock price predictions. Signal ratings are strictly based on fundamental analysis. Users must perform their own due diligence and consult financial advisors, as all investments carry inherent risks, including principal loss. The system is presented as a specific edition from late 2025.

Health Check
Last Commit

1 month ago

Responsiveness

Inactive

Pull Requests (30d)
1
Issues (30d)
1
Star History
55 stars in the last 30 days

Explore Similar Projects

Feedback? Help us improve.