Broker API HubMenu

Lumiwealth/lumibot

Flow diagram titled AI Trading Team Workflow. Evidence sources (market data, news, SEC filings, financial statements, FRED macro, technical indicators) feed a Research Agent, then a Bull Agent and a Bear Agent, then a Portfolio Manager Agent, then Lumibot Execution with backtest, paper and live modes.
A diagram from the README of a strategy built from four AI agents: research, a case for, a case against, and a portfolio manager that passes orders to Lumibot. Image from the repository's README. Copyright the Lumiwealth/lumibot authors. Licence: GPL-3.0. Source file on GitHub, copied and resized. How images are chosen.

In its own words: AI agents that actually place the trade. 12 brokers, real backtests, stocks options futures forex crypto and prediction markets.

Independent and unofficialRead from GitHub

Open Lumiwealth/lumibot on GitHub

Risk warning: CFDs and spread bets are complex instruments and come with a high risk of losing money rapidly due to leverage. You can lose money on these products, and each provider publishes its own loss figure under FCA rules. You should consider whether you understand how they work and whether you can afford to take the high risk of losing your money. Automated and API trading can amplify losses through bugs, connectivity failures and runaway orders.

The facts

Stars
2,102
Forks
411
Language
Python
Licence
GPL-3.0
Created
Last push
Kind
Backtesting and research
Read from GitHub
github.com/Lumiwealth/lumibotchecked

Stars measure attention, not quality or safety. Nothing here reviews the code or its author. Read the licence, the open issues and the code itself before you run anything against an account. Star velocity: unmeasurable, because this site holds one reading for this repository.

Get started in a couple of minutes

You need Python and Git installed. Then, in a terminal:

git clone https://github.com/Lumiwealth/lumibot.git
cd lumibot
  1. python -m venv .venv
  2. Activate it: .venv\Scripts\activate on Windows, source .venv/bin/activate on macOS or Linux
  3. Install what the project needs. Most Python projects use: pip install -r requirements.txt or pip install -e .

These are the usual steps for a project in this language, not instructions taken from this repository. Its README has the exact commands, and it wins wherever the two differ.

Before you connect anything to a broker: read what the code does, use a demo account, and keep keys in environment variables, never in the code. New to GitHub? Start with the basics.

Use it with

Others of the same kind