Summaries and key ideas, written by Stratmill's research agent, of the books, papers, articles and code our AI agents read. Each page links to its original.
84 documents
This example describes a concentrated long-only stock portfolio built through a sequence of AI agents. A research agent ranks companies for understandable businesses, cash generation, and attractive prices. A second agent challenges each idea by examining…
This example organizes daily decisions across leveraged sector and broad-market ETFs using separate AI agents for technology, financials, healthcare, energy, and consumer-related groups. Each sector pod is instructed to consult recent news and macroeconomic…
This strategy looks for an intraday recovery after SPY falls at least 0.15% below VWAP and then closes back above it. A research agent checks the setup hourly, beginning only after 10:00, while a separate trading agent decides whether to enter. It buys only…
This bot aims to mirror a named member of Congress’s reported stock holdings. A research agent checks House disclosure filings, using annual reports as the starting portfolio and applying later trade reports to update it. It excludes options, real estate,…
This strategy uses a public disclosure page as a signal for trading stocks or exchange-listed units. A research agent retrieves the page and checks when it was published; the strategy proceeds only when the disclosure predates the trading session and reports…
This report presents a short backtest of a large-cap stock strategy attributed to a multi-agent AI trading bot and compares it with SPY. The stated test ran from January 4 to January 15, 2026, using Yahoo data and a universe of large technology and other…
This example outlines a disclosure-following workflow based on public House periodic transaction reports. It distinguishes the transaction date from the date a filing becomes public, and says a strategy should only make a record available from publication…
This report presents a short backtest of a strategy labeled “momentum-news-generic” against SPY, using Yahoo data. Over the stated period, the strategy had a slightly negative total return, negative annualized return, negative Sharpe and Sortino ratios, and…
This FAQ describes LumiBot, a Python framework for backtesting and live algorithmic trading across several asset classes and brokers. It outlines the shared strategy workflow, data-source requirements, and common operations such as handling fills, tracking…
This document describes a command-line tool for creating, backtesting, and running editable LumiBot strategies. Its ordinary Python template demonstrates a long-only moving-average rule: retrieve recent daily prices, compare the latest close with a rolling…
The document explains how to use ThetaData as a historical data source for LumiBot backtests covering stocks and options, as well as other asset types. It supports minute and daily bars directly; hourly bars can be built from minute data. Downloaded data is…
This comparison surveys AI-oriented trading and research projects by their agent workflows, ability to replay or backtest decisions, broker paths, deterministic strategy support, and hosting or monitoring features. It distinguishes research-focused tools…
This document presents a QuantStats tear sheet for a strategy labeled “buffett-plain,” compared with SPY over January 4–15, 2026. It lists returns, drawdowns, risk-adjusted statistics, market exposure, daily outcomes, and two drawdown episodes. The reported…
This guide explains how advanced users can run Lumibot backtests with their own historical data. It supports intraday and daily testing and describes assets including stocks, futures, cryptocurrency, and foreign exchange. Input data must be converted into a…
The script describes a daily SPY allocation strategy driven by CNN’s Fear and Greed Index. A research agent retrieves the latest score from a prior day, while a separate trading agent maps score ranges to target allocations: higher equity exposure at low…
This code outlines a daily trading workflow in which separate AI agents research a universe of leveraged exchange-traded funds, argue bullish and bearish cases, and pass their summaries to a trading judge. The universe includes leveraged long and inverse…
This document presents a QuantStats tear sheet for a strategy labeled “insider-plain,” compared with SPY over January 4–22, 2026. It reports a 1% total return for the strategy and 0% for the benchmark, with annualized returns of 11.59% and 3.78%,…
The document describes an automated U.S. equities strategy that reconstructs a member of Congress’s reported stock portfolio from annual disclosures and subsequent transaction filings. A research agent combines the year-end holdings with later reported…
This documentation page catalogs practical Python examples for algorithmic trading, including buy-and-hold, momentum, bracket orders, historical data retrieval, quotes, technical indicators, position handling, persistent strategy state, and logging. It…
This page catalogs trading bot examples built around AI agents, ranging from copying reported investor or insider holdings to sentiment signals, agent debates, options strategies, intraday rules, and macro or sector portfolio discussions. It outlines…
This code describes a deterministic replay process for trading on congressional disclosures. It uses each disclosure’s public publication time to decide whether the information was available, explicitly avoiding the transaction date as the signal timestamp.…
This documentation explains how to use Polygon as a historical price-data source for LumiBot backtests across stocks, options, forex, and cryptocurrencies. It describes supplying an API key, selecting a backtest date range, and running a simple example…
The document outlines an intraday SPY strategy that buys after price dips at least 0.15% below VWAP and then returns above it. A research agent checks minute bars hourly beginning at 10:00 ET, while a trading agent enters when the bounce is identified and no…
This example describes an AI-assisted value-investing workflow inspired by Warren Buffett’s public approach. One agent reviews filings and assesses business quality, cash generation, balance-sheet strength, and durability. A second challenges the valuation…