AI tools, scored for your job
Get paid to train AI
🤝 You're in the Free & Open Source library — community-built tools you can use without paying. A different concept from our scored AI directory.
Home › Free & Open Source › Finance › AI Berkshire
✦ Free & open sourceFinance

AI Berkshire

A value investing research framework for Claude Code and Codex combining 4 masters' methodologies.

AI-Era Berkshire Value Investing Framework

Systematize Buffett, Munger, Duan Yongping, and Li Lu methodologies into multi-agent research.

Free forever · open source · MIT
✓ Light setup✓ Browser-based✓ Real-time collaboration
7.8
ZEKAI
Rigorous AI value investing
Free & open source · Finance
Ease of setup4
Usefulness9
Maintenance9.5
Community8.5
★ 16,510
GITHUB
Sep 2026
UPDATED
MIT
LICENSE
🛠 Don't want to self-host? We can set it up →
⚡ Quick answer

ai-berkshire is an open-source investment research skill collection built for Claude Code and Codex. It is designed for serious value investors who want to move past generic AI responses into structured, multi-perspective financial analysis.

Runs on
Cross-platform
Hosting
Desktop
Languages
HTML
License
MIT

What it is

The framework orchestrates 20 specific skills and multi-agent teams to evaluate companies through the lenses of Warren Buffett, Charlie Munger, Duan Yongping, and Li Lu. It includes financial rigor checking, automated screening checklists, and adversarial thesis verification.

Who it's for

It suits quantitative or fundamental value investors who already use AI coding assistants and want a rigorous, repeatable investment framework. It does not suit casual investors looking for quick stock tips without deep data processing.

Key features

4 Masters' Methodologies

Evaluates stocks through conflicting perspectives of Buffett, Munger, Duan, and Li Lu.

Multi-Agent Research Teams

Spawns 4 independent agent analysts to cross-examine data and stress-test assumptions.

Financial Rigor Validation

Uses Python decimal calculations and dual-source verification to prevent decimal errors.

Structured Anti-Bias Rules

Implements quality screens, reverse Munger checks, and quick-veto blacklists.

How to start

Up and running in 3 steps

1
Install the required AI client CLI such as Claude Code or Codex.
2
Clone the ai-berkshire repository to your local machine.
3
Run the provided installation script to load the skills into your global commands directory.
Real talk

Our honest verdict

What's great

  • Forces definite investment conclusions instead of neutral balanced summaries.
  • Built-in financial rigor checks avoid LLM math and unit conversion errors.
  • Comprehensive suite of 20 distinct skills covering screening, thesis tracking, and earnings.
  • Multi-agent adversarial analysis exposes hidden risks and blind spots.

Where it falls short

  • High token consumption due to multi-round research, cross-validation, and multi-agent loops.
  • Requires using command-line AI tools like Claude Code or Codex.
  • Manual script installation required for global command setup.
Cost

Pricing & license

The software is free under its MIT license. The only cost is running it yourself via your AI client API tokens.

Paid work

Open remote AI-training roles

880 open remote AI-training roles, updated November 15, 2026; most pay $20–$175 an hour. Zekai lists them free; the application goes to the employer’s platform.

See all open roles →
Compare

Alternatives

🎁 Free & open-source alternatives

These reviewed AI tools do the same job instantly — from our scored directory.

Get more

Use it, or have us set it up

📄 Free PDF: AI Berkshire for Finance
A plain-language guide to getting your first result. Sent to your inbox.
🔔 64 people want a full video tutorial — add your vote
🛠 Don't want to set it up yourself?
We'll install, host & configure AI Berkshire for you — and train your team.
Get it done for you ↗
Questions

FAQ

Can I just ask Claude these questions directly?

Direct prompts yield balanced, generic summaries. This framework enforces strict conclusions, price tiers, and multi-agent adversarial tension.

How does it handle financial math accuracy?

It utilizes Python scripts with decimal arithmetic and requires cross-verification across at least two independent data sources.

Does this require a paid subscription?

The framework is open source under the MIT license, but running deep research queries will consume significant API tokens through your chosen AI client.

Radar

Latest AI news

✉️ The weekly free toolkit
The best new free & open-source tools for Finance — one short email a week, in your language.
Free · 1 email/week · unsubscribe anytime
Get paid to train AI →

See Zekai first in Google