ValuefocusValuefocus
Get the app
Fundamental Analysis · GitHub

xbtlin/ai-berkshire

An AI-era value investing research framework based on the methodologies of Buffett, Munger, Duan Yongping, and Li Lu, featuring multi-agent parallel research.

85VF score
Maintainer
xbtlin
Market coverage
China A-shares, Global Markets
GitHub stars
12,670
Updated
2026-07-11T00:49:44Z
Best for

Fundamental analysis and intrinsic value estimation for long-term value investing.

Implementation statusGuide reviewed · 2026-07-11T00:49:44Z
Implementation status

MIT

Expected result

Multi-agent adversarial analysis

Known failure mode

Potential LLM hallucinations

Compatibility

China A-shares, Global Markets

Why it stands out

  • Multi-agent adversarial analysis
  • Fundamental methodology integration
  • Automated financial reporting synthesis

Risks and limitations

  • Potential LLM hallucinations
  • Requires high-quality financial data input
  • Not for short-term trading

Examples and expected outcomes

Example 1

Create a repeatable research memo

  • Sourced evidence
  • Repeatable steps
  • Explicit uncertainty
Example 2

Compare companies with one checklist

  • Sourced evidence
  • Repeatable steps
  • Explicit uncertainty
Example 3

Build a sourced bull/bear review

  • Sourced evidence
  • Repeatable steps
  • Explicit uncertainty

Access requirements

Keys and runtime

LLM API Key (Anthropic or OpenAI), Financial Data API Key (Verify current documentation)

License and data rights

MIT

Rate limits

Verify current documentation

Connect to your Agent

Claude config
git clone https://github.com/xbtlin/ai-berkshire && cd ai-berkshire && pip install -r requirements.txt

# Project-scoped Agent Skill layout
.claude/skills/xbtlin-ai-berkshire-review/SKILL.md
.claude/skills/xbtlin-ai-berkshire-review/references/

# Restart Claude Code and confirm discovery.
Prompt example

“Use xbtlin/ai-berkshire to research AAPL. List sources and timestamps first, then separate facts, calculations, risks and missing data. Do not give personalized trading advice.”

When not to use it

  • Potential LLM hallucinations
  • Requires high-quality financial data input
  • Not for short-term trading
Installation

xbtlin/ai-berkshire

Terminal
git clone https://github.com/xbtlin/ai-berkshire && cd ai-berkshire && pip install -r requirements.txt

Before you install

Review the current license and source code, pin a version, keep credentials out of prompts, and start with read-only permissions.

Project-specific questions

What can xbtlin/ai-berkshire do in a real workflow?

Multi-agent adversarial analysis Fundamental methodology integration Automated financial reporting synthesis

What access and compatibility does xbtlin/ai-berkshire require?

MIT · China A-shares, Global Markets

What is the main implementation risk with xbtlin/ai-berkshire?

Potential LLM hallucinations Requires high-quality financial data input Not for short-term trading

View sourceExplore agent setup templates