Value investment research with artificial intelligence
AI-berkshire is a value investing research framework that implements the methodologies of investors such as Warren Buffett and Charlie Munger, using the Claude Code infrastructure. The system analyzes financial data with its multi-agent structure and conducts adversarial reviews.
Updates
- October 29, 2026: Stars 15,925 → 16,931, latest release v1.0.0 (April 7, 2026).
- August 27, 2026: Stars 14,888 → 15,925, latest release v1.0.0 (April 7, 2026).
- August 2, 2026: Stars 2,500 → 14,888, latest release v1.0.0 (April 7, 2026).
What you get
- Structured analysis with the methodology of four investment masters
- Oppositional in-depth investigation with multiple AI agents
- High accuracy and error checking in numerical data
Installation
npm install -g @anthropic-ai/claude-codegit clone https://github.com/xbtlin/ai-berkshire.git
# 复制 skills 到 Claude Code 全局 commands 目录
cp ai-berkshire/skills/*.md ~/.claude/commands/If you don't write code
You, as an investment analyst, analyze the company I choose using the methodologies of Warren Buffett, Charlie Munger, Duan Yongping and Li Lu. In your analysis, evaluate not only financial data, but also the sustainability of the business model, competitive advantages (moat), management quality and possible risks from four different perspectives. Use independent sources to verify information, prefer to say 'I don't know' in ambiguous situations, and provide strategic advice with a clear price range for the investment decision.
Repository: https://github.com/xbtlin/ai-berkshire. Follow the official instructions in the README of this repository for setup and execution.
Before starting, check which OS we are on and if the necessary tools (e.g., Python, Node.js, Git, Docker) are installed. Install any missing ones step-by-step according to this system.
Create a new, empty folder to work in. Do not touch any files outside this folder and do not delete anything. Tell me what you are going to do in one sentence before running each command.
Tell me what I should see on the screen at the end of each step. If an error occurs, I will paste the error message to you exactly as it is, and we will fix it together.
Related dictionary terms
Links
TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-06-26: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. The introductory text was prepared with AI from the repository's own documentation, and this page was machine-translated from the Turkish original · the Turkish version prevails.