SystemSelf reportedCryptoPythonaibinancecryptocurrencynewsprototype

ai-trading-prototype

Free open source crypto AI trading bot prototype.

System Structure

Data Used

Binance가격/거래량 데이터

Rules / Strategy

저장소별 전략/실행 조건 확인 필요

Execution

거래소 API 기반 자동 주문 실행

Editor Summary
저장소 설명과 공개 메타데이터 기준으로 AI/LLM 또는 머신러닝 활용, Python 기반 구현, 암호화폐 거래 봇, 거래소 API/프레임워크 성격의 프로젝트로 파악했습니다. 확인 근거는 README, 저장소 토픽, 저장소 설명, GitHub 지표, 파이프라인 필드이며, 주요 데이터는 Binance, 가격/거래량 데이터입니다. 전략/실행 조건은 저장소별 문서와 코드 확인이 필요하며, 실행 방식은 "거래소 API 기반 자동 주문 실행"라고 보수적으로 기록했습니다. GitHub 지표는 별 145개, 포크 39개입니다.

Repository	binance/ai-trading-prototype
Creator	binance
Stars / Forks	★ 145 / 39
License	MIT
Last Updated	2023-12-30
Snapshot Date	2026-07-08 (README below is a copy from this date)

This is third-party open-source code. QuantField does not guarantee its behavior or safety. Review the code before installing or running it.

View on GitHub →

README

AI Trading Prototype

This project uses OpenAI to determine the sentiment of cryptocurrency news headlines and subsequently executes orders on the Binance Spot Market.

It is composed of two main components: Sentiment Generator and Trading Bot.

Data Flow Diagram

Disclaimer

This project is for demonstration purposes only and has never been executed on a production site. We do not know whether this project can generate profits and don’t hold any responsibility for any losses that may be incurred. You should NOT use this project in your own trading application.

Features

Decoupled Architecture: The two main components can function autonomously on different machines or on the same machine.
Sentiment Persistence: The generated sentiments can be either persisted locally or broadcasted over Redis.
Redis Publish/Subscribe Messaging Paradigm: The generated sentiments events can be real-time accessed by the Trading Bot or any other subscriber to the same Redis channel.
Option to define your variables for the default trading strategy.
Trading Bot Dry-run: Configure the Trading Bot with Spot Testnet URL to test without costs.
Trading Bot Backtesting: Run a simulation of the trading strategy for historical headlines by using ai-trading-prototype-backtester.
News Headlines Retrieval: News headlines to feed Sentiment Generator can be retrieved by using ai-trading-prototype-headlines.

Requirements

Signature Generator:

OpenAI API key with enough credit to cover the gpt-3.5-turbo max 4K context usage. The costs depends on the amount of provided headlines and the length of the same.
(Optional) If you decide to use Redis, you need to have a running instance of Redis Server.

Trading Bot:

Binance Exchange Spot API Key or Binance Spot Testnet API key.
A running instance of Redis Server

Installation

Clone from GitHub:

git clone git@github.com:binance/ai-trading-prototype.git

Install the required libraries:

cd <path_to_cloned_repository>
pip install -r requirements.txt

Usage

Commands

usage: aitradingprototype [-h] (-sg | -tb) config_file

Free open source AI trading bot prototype

positional arguments:
  config_file           .YAML config file for sentiment_generator or trading_bot process

optional arguments:
  -h, --help            show this help message and exit
  -sg, --sentiment_generator
                        starts the sentiment generator process
  -tb, --trading_bot     starts the trading bot process

Sentiment Generator and Trading Bot

The complete AI Trading is achieved by running two processes simultaneously: One to use the [Sentiment Generator](#sentiment-ge