ai-berkshire
An AI-powered multi-agent parallel research framework providing professional-grade investment decision support.
- Region
- Domestic
- Pricing
- Free
- Open source
- Yes
- GitHub Stars
- ★ 4.0k
- Source
- GitHub
- Added
- 2026-06-28
- Last verified
- 2026-06-28
Overview
AI Berkshire is a skill suite for investment research compatible with Claude Code and Codex, systematically and structurally integrating the value investing methodologies of Warren Buffett, Charlie Munger, Dong Yongping, and Li Lu. Through parallel multi-agent research, it enables professional-level investment analysis. The framework includes multiple bias-prevention mechanisms and precise calculation tools to ensure rigor and reproducibility in research outcomes. Suitable for individual investors and teams, it helps users conduct deep investment analysis and informed decision-making.
Key features
- ▪Multi-agent parallel research
- ▪Integration of four master investors' methodologies
- ▪Forces clear conclusions—no ambiguity
- ▪Structured anti-bias mechanisms
- ▪Precise financial data computation
Use cases
Pros
- ＋Multi-perspective adversarial analysis
- ＋Reproducible research workflow
- ＋High data accuracy
- ＋Well-suited for team collaboration
Limitations / notes
- －Requires internet connection
- －Higher learning curve
Who it's for
This overview was compiled by AI from public sources and may contain inaccuracies — please refer to the official site.
FAQ
Is it free?
The project is open source, but specific usage may incur API costs.
Do I need scientific internet access?
Some features may require access to foreign websites; using scientific internet access is recommended.
Does it support Chinese?
Yes, both documentation and output are available in Chinese.
Can it be used commercially?
Yes, it can be used commercially, but must comply with relevant open-source licenses.
Similar agents
ai-data-science-team
An AI-powered data science team that helps you complete common data science tasks faster.
Better Stack | AI SRE Agent
AI agent with infrastructure knowledge for incident handling.
vika维格云
An intelligent multi-dimensional table and data productivity platform that supports one-click AI training.
InternAgent
InternAgent-1.5 is a unified autonomous scientific discovery framework supporting long-term autonomous scientific research.
TabTab
The first end-to-end Data Agent for data processing and analysis.
llm_wiki
LLM Wiki is a cross-platform desktop application that automatically transforms documents into organized, interlinked knowledge bases.
Something wrong? Let us know on the About page and we'll fix it.