lumibot
Lumibot is a platform for building and backtesting AI trading agents and Python algorithmic trading strategies for stocks, options, cryptocurrencies, and more.
- Region
- Overseas
- Pricing
- Free
- Open source
- Yes
- GitHub Stars
- ★ 1.7k
- Source
- GitHub
- Added
- 2026-06-12
- Last verified
- 2026-06-12

Overview
Lumibot is an open-source Python library that enables users to build testable AI trading agents and algorithmic trading strategies. It supports multiple asset types including stocks, options, cryptocurrencies, futures, and forex. Users can create deterministic strategies or AI-based strategies and backtest them using historical data. Additionally, Lumibot supports paper trading and live trading, allowing users to test and execute strategies on the same codebase. The platform is ideal for developers and investors looking to leverage AI and algorithms for trading.
Key features
- ▪Supports multiple asset types
- ▪Testable AI trading agents
- ▪Supports paper trading and live trading
- ▪Built-in AI agent runtime
Use cases
Pros
- +Open source and free
- +Supports multiple asset types
- +Flexible strategy development
- +Powerful backtesting capabilities
Limitations / notes
- -Requires some Python programming experience
- -Higher learning curve
Who it's for
This overview was compiled by AI from public sources and may contain inaccuracies — please refer to the official site.
FAQ
Is it free?
Yes, Lumibot is open source and free.
Does it support Chinese?
Documentation is primarily in English, but community resources may include Chinese content.
Can it be used commercially?
Yes, Lumibot is licensed under the MIT license.
Similar agents
Cursor
FeaturedAI-powered code editor with Agent mode
Dify
FeaturedOpen-source LLMOps + Agent orchestration platform
扣子 Coze
FeaturedByteDance's no-code Agent/Bot building platform
Trae
FeaturedAI IDE (with Agent) from ByteDance
LangChain
FeaturedThe most mainstream LLM/Agent orchestration framework
Devin
FeaturedAutonomous software engineer Agent by Cognition
Something wrong? Let us know on the About page and we'll fix it.