gitwtfhub

wtf is warren-buffett-jr?

infusionvictor/warren-buffett-jr — explained in plain English

Analysis updated 2026-05-18

17PythonAudience · researcherComplexity · 3/5Setup · easy

TL;DR

A six-agent stock research system, built on Claude Code, that scores US companies on fundamentals, technicals, and valuation.

Mindmap

mindmap
  root((Warren Buffett Jr))
    What it does
      Six specialist agents
      100 point score
      Bull Medium Bear targets
    Tech stack
      Python
      Claude Code
      SEC EDGAR data
    Use cases
      Score a US stock
      Discover growth companies
      Run full agent report
    Audience
      Individual investors
      Researchers

Code map

Detail Auto

An interactive map of this repo's files and how they connect — its source is parsed live in your browser. Click Visualize to build it.

filefunction / class

Why would anyone build with this?

REASON 1

Search any US ticker and get a plain-English scorecard with bull, medium, and bear price targets.

REASON 2

Discover mid-sized, profitable, growing companies using the built-in screener.

REASON 3

Run a full six-agent research report on a stock directly inside Claude Code.

REASON 4

Use the command line tool to analyze, scorecard, or screen stocks in scripts.

What's in the stack?

PythonClaude CodeSEC EDGAR APIYahoo Finance

How it stacks up

infusionvictor/warren-buffett-jr0petru/sentimoagi-eval-official/forte
Stars171717
LanguagePythonPythonPython
Setup difficultyeasymoderatehard
Complexity3/53/54/5
Audienceresearcherdeveloperdeveloper

Figures from each repo's GitHub metadata at analysis time.

How do you spin it up?

Difficulty · easy Time to first run · 30min

No API keys are required to start, optional FMP, FinnHub, and FRED keys enrich the data.

Wtf does this do

Warren Buffett Jr is a multi-agent stock analysis system built on top of Claude Code, following a methodology called Ruta 2030 Wall Street Agent System. A main orchestrator agent coordinates six specialist sub-agents that each look at a stock from a different angle: business quality, financial health, market and growth trends, technical momentum, risk and resilience, and valuation. Each specialist works independently and does not see the others' scores until all six are finished, so a strong valuation cannot quietly cover up weak fundamentals, or the other way around. The final report combines all six into an auditable score out of 100 points. The project follows a strict rule: without evidence there is no number, without a number there is no score, and without a formula there is no conclusion. If the data needed for a section is missing, the system marks that part as not scorable instead of filling the gap with a confident sounding guess. There are two ways to use it. A web app, built in Python, lets you search any US company by ticker or name and see a plain language explanation, a 1 to 10 scorecard from the agents, and a 12 month price chart with bull, medium, and bear targets. It also includes a screener that surfaces mid sized, profitable, growing companies you might not already know. A command line tool offers the same analyze, scorecard, and screen actions. No API keys are required to start, since core financial data comes from the free SEC EDGAR filings and Yahoo price data, though you can add optional API keys for extra data sources. The second way is the full six agent system, run from inside Claude Code by simply asking it to analyze a ticker, the orchestrator then builds the data packet, runs the six specialists, and produces the full audited report. The README notes that this deeper Python engine, covering technical indicators and a full valuation model, is still being built. The project states clearly that its output is research only, with stated assumptions, not investment advice, and it never places trades on its own.

Yoink these prompts

Prompt 1
Analyze NVDA using the Warren Buffett Jr multi-agent system in Claude Code.
Prompt 2
Walk me through setting up the warren-buffett-jr web app locally with Python.
Prompt 3
Explain what the six specialist agents in warren-buffett-jr each score and why they run independently.
Prompt 4
Show me how to add my own FMP, FinnHub, or FRED API keys to warren-buffett-jr for richer data.

Frequently asked questions

wtf is warren-buffett-jr?

A six-agent stock research system, built on Claude Code, that scores US companies on fundamentals, technicals, and valuation.

What language is warren-buffett-jr written in?

Mainly Python. The stack also includes Python, Claude Code, SEC EDGAR API.

How hard is warren-buffett-jr to set up?

Setup difficulty is rated easy, with roughly 30min to a first successful run.

Who is warren-buffett-jr for?

Mainly researcher.

View the repo → Decode another repo

This repo across BitVibe Labs

Don't trust strangers blindly. Verify against the repo.