Practice Buffett-style Value Investing

English · 简体中文

This project has no association, sponsorship, endorsement, or authorization relationship with Mr. Warren Buffett or Berkshire Hathaway Inc.
If you like AiBuffett, please give us a ⭐ on GitHub!

Introduction

AiBuffett is a professional investment analysis AI agent that helps automate the generation of high-quality fundamental company research reports. It integrates multiple built-in analytical models, deeply incorporates Buffett's investment philosophy, and applies value investing principles to provide investors with professional investment decision support.

1. Architecture

2. Feature

AiBuffett provides comprehensive and in-depth fundamental analysis across the following dimensions:

• Business Model Analysis: In-depth interpretation of the company's core business and competitive advantages.
• Revenue Analysis: Quantitative assessment of revenue structure and growth quality.
• Development Prospects Analysis: Forward-looking evaluation of market potential and growth space.
• Profitability Analysis: Comprehensive examination of profit margins and capital return levels.
• Operational Stability Analysis: Systematic diagnosis of financial health and risk resilience.
• Guidance Analysis: Accurate understanding of performance expectations and future development direction.
• Management Analysis: Qualitative assessment of governance structure and management execution capabilities.
• Valuation Analysis: Determination of a reasonable value range using multiple valuation models.

In the end, the system delivers a comprehensive evaluation and analytical conclusion based on Buffett's value investing philosophy.

Quick Start

1. How to Install

Before you can run the AiBuffett, you'll need to install it and set up your API keys.

1.1 Clone the Repository

git clone https://github.com/Hayden-CHENPRO/AiBuffett.git
cd AiBuffett

1.2 Set up API keys

Create a .env file for your API keys:

# Create .env file for your API keys (in the root directory)
cp .env.example .env

Open and edit the .env file to add your API keys:

# (required) Use Google APIs for searching, thinking, summarizing and tool calls
GOOGLE_API_KEY="..."

# (optional) Use langsmith to track the overall process and token consumption
LANGSMITH_TRACING="true"
LANGSMITH_API_KEY="..."

# (optional) Use a specified model other than Gemini for some of the sections
OPENAI_API_KEY="..."
OPENAI_API_BASE="..."

1.3 Install the Environment

# Use uv to quickly install the environment
uv sync

2. Example Use Cases

# activate the environment
source .venv/bin/activate

# run the AiBuffett
uv run main.py "UNITEDHEALTH GROUP INC" "UNH"

Note:

• The two main parameters of the program are the full company name (e.g. "UNITEDHEALTH GROUP INC") registered with the SEC and the corresponding company ticker (e.g. "UNH").
• Currently, only U.S.-listed companies are supported.
• All project parameter settings are located in the configuration.py file.

3. Example Outputs

1. APPL Fundamental Analysis Report - English Version
2. APPL Fundamental Analysis Report - Chinese Version
3. UNH Fundamental Analysis Report - English Version
4. UNH Fundamental Analysis Report - Chinese Version

Next Step

1. Enhance the efficiency of the architecture: Currently, a single task takes approximately 20 minutes and consumes about 200,000 tokens.

Acknowledgments

1. gemini-fullstack-langgraph-quickstart
2. ai-hedge-fund

License

This project is licensed under the Apache License 2.0. See the LICENSE file for details.