xbtlin/ai-berkshire

Berkshire in the AI era: a value investing research framework built for Claude Code / Codex. Buffett, Munger, Duan Yongping, and Li Lu's methodologies + multi-agent adversarial analysis.

About the project

AI Berkshire is a collection of Claude Code and Codex skills that structures investment research around the methods of four value-investing thinkers and uses multiple agents for adversarial analysis. It is intended for investors who want a disciplined process for researching companies and making valuation-based decisions.

Latest release v1.0.0 — v1.0.0 - AI Berkshire 首发 · 7 Apr 2026

These files are xbtlin/ai-berkshire's own configuration. They tell Codex, OpenCode and Claude Code how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.

16,195Stars on the repository
2Files it configures its agents with
2,391Tokens loaded in every session
3Agents configured
▶ Install AI Berkshire GitHub Review & Guide: Institutional-Grade Investment Research with Claude Code Alex Hitt · about xbtlin/ai-berkshire · on YouTube →

Instructions