隐私与广告选择
Git-Stars 会使用必要存储来保障网站运行。可选分析和广告测量脚本默认不加载，只有在你同意后，Google 等合作伙伴才可能按要求使用 Cookie 或类似标识符。 隐私政策
AI 时代的伯克希尔：基于 Claude Code / Codex 的价值投资研究框架。巴菲特·芒格·段永平·李录四大师方法论 + 多Agent并行研究。| AI-era Berkshire: a value investing research framework built for Claude Code / Codex. 4 masters' methodologies + multi-agent adversarial analysis.
这个仓库详情页已经具备足够的原创分析、来源证据和同类对比，可以作为 Git-Stars 的可索引评测页。
85
评测分
解决的问题
It addresses the inefficiency and subjectivity of manual value investing research by leveraging AI agents to systematically apply proven investment frameworks, enabling faster, more consistent, and multi-perspective analysis of companies.
部署现实
当前可用的安装信号是：Clone the repo and run `pip install -r requirements.txt` (or equivalent setup command as specified in the project's README).。这只能作为起点，正式使用前建议让 Codex 或 Claude 检查 README、环境变量、运行时版本和部署目标。
商业可用性
当前记录的许可证是 MIT。这是重要的商业使用信号，但仍应核验许可证全文、依赖许可证、模型/API 条款和商标限制。
能力上限
Developers can build automated investment research pipelines that analyze financial reports, news, and qualitative data using the four masters' criteria. Real-world use cases include screening for undervalued stocks, generating investment memos, and conducting adversarial debates between agents to stress-test investment theses. The ceiling includes fully autonomous portfolio monitoring and decision support systems.
Git-Stars 是独立产品，不隶属于 GitHub 或该项目。 分析可能由 AI 辅助生成，依据公开仓库元数据和 README 的短摘要。 我们不镜像完整 README、文档、Issue 或社媒评论。
xbtlin/ai-berkshire 被追踪为 Python 项目，主要属于 AI Agent, MCP Server, LLM Tool, UI Framework 方向。这个评估结合公开 GitHub 元数据、分类信号、短来源摘要和 Git-Stars 编辑规则，而不是复制项目文档。
增长检查：该仓库目前有 15k Star，今日 +0，本周 +0，本月 +9.7k。这些窗口用于区分持续采用信号和短期曝光峰值。
维护检查：当前活跃度为 一般；最近一次推送距今 79 天，未关闭 Issue 为 28，约占总 Star 的 0.19%。这只是采用信号，不替代工程尽调。
采用检查：2.1k Fork 和 15k Watcher 反映项目被复用和关注的程度。许可证信号：MIT。商业或内部使用前请核验许可证兼容性。
适用判断：当你需要「AI 原型、LLM 工作流和 Agent 类应用」时，这个项目更值得评估；如果「需要法律审查、安全审计或生产 SLA 保证」，则需要谨慎。
来源检查：Git-Stars 当前为这份报告保留了 2 个明确来源引用，近期增长信号为 9.7k。最终安装、安全和版本信息仍应以原始 GitHub 仓库为准。
原创分析
充分已经具备问题、能力和结论层面的原创判断。
来源
充分已附带仓库元数据和 README/来源引用。
许可证
充分已记录 MIT，可作为评估依据。
维护
充分仓库元数据中可以看到近期活跃信号。
同类对比
充分已有足够相近项目用于对比。
热度
15k 星标
复用
2.1k 复刻
关注
15k 关注者
维护
moderate
许可证
MIT
未解决 Issue
28
AI Berkshire is a value investing research framework designed for Claude Code / Codex, integrating the methodologies of four legendary investors (Buffett, Munger, Duan Yongping, Li Lu) with multi-agent adversarial analysis to automate and enhance investment research.
AI Agent
Agent frameworks, autonomous workflows, and tool-use systems
MCP Server
Model Context Protocol servers, clients, and integrations
LLM Tool
Libraries and tools for LLM apps, RAG, prompts, and evals
UI Framework
Frontend frameworks, design systems, and interface libraries
Clone the repo and run `pip install -r requirements.txt` (or equivalent setup command as specified in the project's README).70
健康评分
一般
提交活跃度
Apr 7, 2026
创建于
Jul 26, 2026
最近提交
每日同步积累数据后，Star 历史将在此显示。
复刻
未解决
关注者
xbtlin
GitHub 主页codecrafters-io/build-your-own-x
Master programming by recreating your favorite technologies from scratch.
sindresorhus/awesome
😎 Awesome lists about all kinds of interesting topics
freeCodeCamp/freeCodeCamp
freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming, and computer science for free.
EbookFoundation/free-programming-books
:books: Freely available programming books
nilbuild/developer-roadmap
Interactive roadmaps, guides and other educational content to help developers grow in their careers.
✓
许可证
✓
Fork 情况
~ 一般
维护情况
解决的问题
It addresses the inefficiency and subjectivity of manual value investing research by leveraging AI agents to systematically apply proven investment frameworks, enabling faster, more consistent, and multi-perspective analysis of companies.
能力范围
Developers can build automated investment research pipelines that analyze financial reports, news, and qualitative data using the four masters' criteria. Real-world use cases include screening for undervalued stocks, generating investment memos, and conducting adversarial debates between agents to stress-test investment theses. The ceiling includes fully autonomous portfolio monitoring and decision support systems.
结论
This framework is ideal for value investors and developers seeking to automate and systematize investment research using AI. It should be avoided by those who prefer discretionary, qualitative-only analysis or lack technical skills. The key trade-off is between efficiency/consistency and the nuance of human judgment.