Repolode
Submit
Lumiwealth

Lumiwealth/lumibot

Python framework for building, backtesting and live-trading stock, options, futures, forex, crypto and prediction-market strategies, with optional AI agents that make trading decisions.

Open-source alternative to:TradingView

View on GitHubWebsite
Stars
2,213
Forks
423
Open issues
116
Last commit
15 hours ago

Repolode describes open-source projects and does not give investment advice. Trading and investing can lose money: assess the risk yourself and follow the laws where you live before using this project.

What is it?

LumiBot is an open-source Python framework for writing trading bots. You can express trading rules directly in Python, delegate decisions to AI agents driven by prompts, or combine both in one strategy.

The same strategy class runs on historical data for backtesting and on a supported broker for paper or live trading; only the data source and broker runner change. The README lists support for 12 brokers across stocks, options, futures, forex, crypto and prediction markets, with Alpaca and Interactive Brokers among the named integrations.

The project includes a CLI, example strategies, a researcher-and-trader two-agent example, and an optional BotSpot MCP connection that gives agents research tools such as economic data, news and SEC filings. Backtests produce charts, trade records and logs.

Key features

  • 01Write strategies in Python, as AI-agent prompts, or as a hybrid of both.
  • 02Backtest on historical data with charts, trades and logs.
  • 03Reuse the same strategy class for paper and live trading through supported brokers.
  • 04Covers stocks, options, futures, forex, crypto and prediction markets.
  • 05Includes a CLI and example strategies to get started.

Use cases

  • Backtesting a rules-based stock or options strategy before risking capital.
  • Prototyping an AI agent that reviews market data and places orders under constraints.
  • Running a paper-trading bot against Alpaca or Interactive Brokers.
  • Comparing a Python rule with an AI-driven decision on the same historical data.

Quick start

  1. 1

    Install LumiBot with pip

    pip install lumibot
  2. 2

    Save the example strategy as my_strategy.py, then run the backtest

    python my_strategy.py

Things to know

  • Licensed under GPL-3.0, a copyleft license that requires derivative works to be open-sourced under the same terms.
  • The AI examples need an OpenAI API key and model calls incur charges.
  • Live and paper trading require an account with a supported broker, such as Alpaca.

In collections

Open-source AI agent frameworks & apps

Topics

#algorithmic-trading#backtesting#ai-agents#python#crypto-trading#stocks#options-trading#trading-bot#agentic-trading#ai-trading

FAQ

What is lumibot?
Python framework for building, backtesting and live-trading stock, options, futures, forex, crypto and prediction-market strategies, with optional AI agents that make trading decisions. LumiBot is an open-source Python framework for writing trading bots. You can express trading rules directly in Python, delegate decisions to AI agents driven by prompts, or combine both in one strategy.
Is lumibot free to use? What license does it have?
lumibot is open source under the GPL-3.0 license. Check the license terms before using it in commercial products.
Is lumibot still maintained?
Actively maintained. The last commit to lumibot was on Nov 6, 2026.
What can I use lumibot for?
Backtesting a rules-based stock or options strategy before risking capital. Prototyping an AI agent that reviews market data and places orders under constraints. Running a paper-trading bot against Alpaca or Interactive Brokers. Comparing a Python rule with an AI-driven decision on the same historical data.
How do I install lumibot?
Install LumiBot with pip: pip install lumibot Save the example strategy as my_strategy.py, then run the backtest: python my_strategy.py
Where can I get lumibot?
The source code and installation instructions are on GitHub: https://github.com/Lumiwealth/lumibot

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects