bbfamily/abu

Analysis updated 2026-06-24

★ 17,126PythonAudience · dataComplexity · 4/5Setup · moderate

Mindmap

mindmap
  root((abu))
    Inputs
      Market data
      Strategy code
      ML models
    Outputs
      Backtest results
      Trading signals
      Charts
    Use Cases
      Backtest a strategy
      Build ML signals
      Trade crypto and stocks
    Tech Stack
      Python
      pandas
      numpy
      matplotlib

mindmap root((abu)) Inputs Market data Strategy code ML models Outputs Backtest results Trading signals Charts Use Cases Backtest a strategy Build ML signals Trade crypto and stocks Tech Stack Python pandas numpy matplotlib

Click or tap to explore — scroll the page freely

What do people build with it?

USE CASE 1

Backtest a stock trading strategy against historical data

USE CASE 2

Build ML-based signals across A-shares, US stocks, and crypto

USE CASE 3

Use the visual interface to build strategies without writing code

USE CASE 4

Pull AI-generated market reports from the companion abuquant.com site

What is it built with?

Pythonpandasnumpymatplotlib

How does it compare?

	bbfamily/abu	kvcache-ai/ktransformers	microsoft/agent-lightning
Stars	17,126	17,156	17,176
Language	Python	Python	Python
Setup difficulty	moderate	hard	moderate
Complexity	4/5	5/5	4/5
Audience	data	researcher	developer

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

How do you get it running?

Difficulty · moderate Time to first run · 1h+

Documentation is mostly in Chinese, non-Chinese readers will need translation help.

In plain English

Abu is an open-source quantitative trading system written in Python. Quantitative trading (or "quant trading") means using math, statistics, and computer algorithms to make buy and sell decisions automatically, rather than relying on human intuition. The system covers multiple asset types including stocks, options, futures, and bitcoin. The platform uses machine learning, software that learns patterns from historical data, to analyze market signals and identify trading opportunities. It integrates tools for data manipulation (pandas, numpy) and charting (matplotlib) to help users build and backtest their own trading strategies. Backtesting means testing a strategy against past market data to see how it would have performed. Abu includes both a code-based interface for developers and a visual, non-programming interface for users who prefer working without writing code. It comes with a web-based companion at abuquant.com that provides real-time AI-generated reports for major global market indices, including Chinese A-shares, US stocks, Hong Kong stocks, gold, oil, and various currency pairs. You would use this if you want to build automated trading strategies, study quantitative finance, or analyze market patterns across stocks, crypto, or commodities, all without paying for an expensive commercial platform. The project is primarily documented in Chinese, so it suits Chinese-speaking traders and investors most naturally.

Copy-paste prompts

Prompt 1

Install abu locally and run the included demo backtest on Apple stock for the last 5 years

Prompt 2

Write a new abu strategy that buys when the 20-day moving average crosses above the 50-day

Prompt 3

Connect abu to a bitcoin price feed and backtest a momentum strategy on hourly bars

Prompt 4

Translate the abu README sections I need to get started since I don't read Chinese

Frequently asked questions

What is abu?

A Python quantitative trading system for stocks, options, futures, and bitcoin. Includes machine learning signals, backtesting, and a no-code visual interface.

What language is abu written in?

Mainly Python. The stack also includes Python, pandas, numpy.

How hard is abu to set up?

Setup difficulty is rated moderate, with roughly 1h+ to a first successful run.

Who is abu for?

Mainly data.

Open on GitHub → Explain another repo

This repo across BitVibe Labs

Scan in gitsafehub Deploy in gitdeployhub bbfamily on gitmyhub

Verify against the repo before relying on details.