Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Python trading framework with AI agents that actually place the trade. Backtest, paper and live trade on 12 brokers: stocks, options, futures, forex, crypto and prediction markets.
| Date | Stars |
|---|---|
| 2026-07-31 | 1862 |
| 2026-08-10 | 1899 |
| 2026-08-18 | 1944 |
| 2026-08-19 | 1948 |
| 2026-08-20 | 1947 |
| 2026-08-21 | 1950 |
| 2026-08-22 | 1952 |
| 2026-08-23 | 1967 |
| 2026-08-24 | 1969 |
| 2026-08-25 | 1974 |
| 2026-08-26 | 1985 |
| 2026-08-27 | 1991 |
| 2026-08-28 | 2005 |
| 2026-08-29 | 2007 |
| 2026-08-30 | 2012 |
| 2026-08-31 | 2016 |
| 2026-09-01 | 2023 |
| 2026-09-02 | 2032 |
| 2026-09-03 | 2038 |
| 2026-09-04 | 2037 |
| 2026-09-05 | 2040 |
| 2026-09-06 | 2043 |
| 2026-09-07 | 2046 |
| 2026-09-08 | 2049 |
| 2026-09-09 | 2050 |
| 2026-09-10 | 2051 |
| 2026-09-11 | 2054 |
| 2026-09-12 | 2056 |
| 2026-09-13 | 2059 |
| 2026-09-14 | 2061 |
| 2026-09-15 | 2063 |
| 2026-09-16 | 2069 |
| 2026-09-17 | 2074 |
| 2026-09-18 | 2073 |
| 2026-09-19 | 2074 |
| 2026-09-20 | 2076 |
| 2026-09-21 | 2079 |
| 2026-09-22 | 2079 |
| 2026-09-23 | 2082 |
| 2026-09-24 | 2087 |
| 2026-09-25 | 2088 |
| 2026-09-26 | 2091 |
| 2026-09-27 | 2096 |
| 2026-09-28 | 2100 |
| 2026-09-29 | 2100 |
| 2026-09-30 | 2101 |
| 2026-10-01 | 2102 |
| 2026-10-02 | 2103 |
| 2026-10-03 | 2100 |
| 2026-10-04 | 2103 |
| 2026-10-05 | 2102 |
| 2026-10-06 | 2104 |
| 2026-10-07 | 2108 |
| 2026-10-08 | 2109 |
| 2026-10-09 | 2112 |
| 2026-10-10 | 2115 |
| 2026-10-11 | 2117 |
| 2026-10-12 | 2119 |
| 2026-10-14 | 2120 |
| 2026-10-15 | 2124 |
| 2026-10-16 | 2129 |
| 2026-10-17 | 2131 |
| 2026-10-18 | 2135 |
| 2026-10-19 | 2136 |
| 2026-10-20 | 2139 |
| 2026-10-21 | 2142 |
| 2026-10-22 | 2143 |
| 2026-10-23 | 2151 |
| 2026-10-24 | 2159 |
| 2026-10-25 | 2168 |
| 2026-10-26 | 2173 |
| 2026-10-27 | 2173 |
| 2026-10-28 | 2179 |
| 2026-10-29 | 2183 |
| 2026-10-30 | 2186 |
| 2026-10-31 | 2188 |
| 2026-11-01 | 2192 |
| 2026-11-02 | 2196 |
| 2026-11-03 | 2200 |
| 2026-11-04 | 2207 |
Today
+7 stars today
This week
+28 stars this week
This month
+105 stars this month
Momentum
116.0
growth rate 1.29%/day
[](https://github.com/Lumiwealth/lumibot/actions/workflows/cicd.yaml)
[](https://github.com/Lumiwealth/lumibot/actions/workflows/cicd.yaml)
[](https://pypi.org/project/lumibot/)
[](https://pypistats.org/packages/lumibot)
[](https://pypi.org/project/lumibot/)
[](LICENSE)
# LumiBot AI Trading
**Build AI trading agents. Backtest them. Trade with the same strategy.**
LumiBot is a **free, open-source Python framework** for building trading bots.
Write your own trading rules, let AI agents make decisions, or combine both.
Backtest on historical data, inspect trades and results, and use the same
strategy class with a supported broker for paper or live trading.
**Full docs:** [lumibot.lumiwealth.com](https://lumibot.lumiwealth.com/?utm_source=github&utm_medium=readme&utm_campaign=lumibot&utm_content=top_docs_link) · **Managed cloud:** [BotSpot.trade](https://botspot.trade/sales?showLogin=1&utm_source=github&utm_medium=readme&utm_campaign=lumibot&utm_content=top_text_link&sample=lumibot_readme_deploy) · **MCP:** [BotSpot for AI coding agents](https://botspot.trade/agents?utm_source=github&utm_medium=readme&utm_campaign=lumibot&utm_content=top_mcp_link)
Read this in [中文](README.zh-CN.md) · [Español](README.es.md) · [Français](README.fr.md) · [Deutsch](README.de.md) · [日本語](README.ja.md) · [한국어](README.ko.md) · [Português](README.pt.md) · [Русский](README.ru.md)
## Why LumiBot?
- **Native AI trading:** agents research, reason and place orders from your prompts.
- **Backtest before trading:** evaluate AI decisions and Python rules on historical data, with charts, trades and logs.
- **Same strategy for backtesting and trading:** keep your strategy class; change the data source and broker runner.
- **Multiple asset classes:** stocks, options, futures, forex, crypto and prediction markets through [supported brokers](https://lumibot.lumiwealth.com/brokers.all.html).
- **The decision reaches a broker.** Inspect the orders, fills and decision records. [How execution works](https://lumibot.lumiwealth.com/execution_gap.html).
**Build faster with BotSpot MCP.** Connect your assistant for free to get LumiBot
strategy-building skills, research data and tools for backtests and deployment.
[See what your assistant gets](#connect-your-ai-assistant).
## Three ways to build a strategy
- **[AI-native strategies](#run-your-first-ai-backtest):** write prompts for trading agents.
- **[Python strategies](#backtest-a-strategy):** write your rules in Python.
- **[Hybrid strategies](#build-a-hybrid-strategy):** combine Python rules and AI decisions.
## Run your first AI backtest
**The trading rules go in the prompt.** Edit `system_prompt` below to change
what the agent does. `initialize()` creates it once; `on_trading_iteration()`
calls it on every iteration. This example has one agent that makes the trading
decisions and places orders.
Use Python 3.10+. This example uses Yahoo daily prices and an OpenAI model;
model calls incur charges.
```bash
pip install lumibot
export OPENAI_API_KEY="your-openai-api-key"
```
Save as `my_ai_strategy.py`:
```python
from datetime import datetime
from lumibot.backtesting import YahooDataBacktesting
from lumibot.strategies import Strategy
class MyAIStrategy(Strategy):
def initialize(self):
self.sleeptime = "1D"
self.agents.create(
name="trader",
default_model="openai/gpt-6-luna",
reasoning_effort="medium",
allow_trading=True,
system_prompt=(
"Trade SPY using its last 20 completed daily bars. "Excerpt of 14,928 characters
Read on GitHub
3.4k
484
375
313
307
269
70
56
20
15
10
10
8
6
5
5
4
4
3
3
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:0748a544c5e9cb3a, topic:ai-agents, topic:multi-agent, readme:ai agent
matched fp:0748a544c5e9cb3a, topic:finance, topic:quantitative-finance