After achieving a two-year return of +1.46 million, someone has open-sourced their own investment research system. The project is called AI Berkshire, and they’ve even shared the live trading results: 2024: +69.29% 2025: +66.38% The core isn’t about 'AI stock picking,' but rather breaking down the investment frameworks of Buffett, Munger, Duan Yongping, and Li Lu into actionable, reviewable research processes. It analyzes companies from perspectives like business model, moat, cash flow, valuation, margin of safety, management, and risk factors. Then, using Claude Code / Codex, multiple agents work in parallel to handle financial report analysis, valuation assessments, cross-validation, and investment memos. What’s most worth learning from this project is that it doesn’t treat AI as an 'answer machine,' but instead organizes the decision-making paths in real investment research into a system that can be repeatedly executed. For individual investors, this might be more valuable than simply asking AI, 'Should I buy this stock?' Project: https://(github.com)/xbtlin/ai-berkshire Not investment advice, just sharing for learning purposes. #AI #Investing #OpenSource