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.
86 documents
This strategy organizes research and trading for same-day-expiration bear call spreads through separate agents. A researcher gathers account and market information, checks the listed expiration, contract Greeks, and bid-ask quality, then identifies a short…
The document describes TradingSlippage as an execution cost applied during backtesting to SMART_LIMIT fills. It says slippage can be supplied at the strategy level, with separate lists for buy and sell orders. This lets a researcher model an assumed cost on…
This guide describes ways to organize AI agents inside a trading strategy, from a single analyst to specialist research teams, opposing bull and bear views, and sequential debate. It distinguishes deterministic strategies, agent-led decisions, and hybrid…
The document contrasts an educational AI investing project, which organizes investor-style agents to debate ideas, with a framework centered on the trading strategy lifecycle. It describes a workflow in which agent decisions are tested on historical data,…
The document contrasts OpenAlice, presented as an AI agent for researching and managing trades across a full lifecycle, with LumiBot, a Python framework for building trading strategies. LumiBot can support deterministic strategies, individual AI agents, or…
This document explains a strategy lifecycle callback invoked when a broker reports a partial order fill. The callback receives the updated position, order, fill price, newly observed fill quantity, and options multiplier. It can support quantity-sensitive…
This repository overview describes a Python framework for building rule-based strategies, AI-assisted decision systems, and combinations of the two. Its central workflow is to test strategy decisions on historical data, inspect simulated orders and reports,…
This Korean-language project overview describes LumiBot, a Python framework for building trading strategies that can use ordinary rules, AI agents, or a combination. It presents a workflow that begins with a sample strategy and historical-data backtest, then…
The document explains a strategy lifecycle method that runs when strategy execution is interrupted. It presents the hook as a place to stop trading gracefully, with selling all assets given as an example action. A brief Python example defines the method on a…
This documentation explains how Lumibot represents cash flows separately from trading activity in strategy backtests and live broker data. It distinguishes deposits and withdrawals from performance while accounting for financing, dividends, fees, interest,…
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 overview describes ways traders and liquidity providers can use decentralized exchange data to understand automated market maker pools. Pool depth and composition can be visualized to estimate capital distribution, likely slippage, and price impact.…
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…
This broker integration guide explains how LumiBot handles Bitunix USDT perpetual futures. It covers account funding, leverage requests, hedge-mode requirements, order precision, reduce-only closes, and historical candle retrieval. The integration does not…
This document describes how to configure Lumibot’s CCXT broker for KuCoin. KuCoin is not presented as a globally auto-detected credential route, so the guide uses an explicit broker configuration with the exchange identifier and API key, secret, and…
This legacy LumiBot guide explains how to connect a trading strategy to Interactive Brokers through Trader Workstation (TWS). It identifies the API settings to enable, including ActiveX and socket clients, and says to turn off read-only access. It…
This guide explains a strategy-level indicator accessor for calculating technical indicators using only market data available at the strategy’s current time. It describes built-in single- and multi-column indicators, Fibonacci retracement levels, and custom…
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 documentation entry directs coding agents to start from complete LumiBot examples for either AI-based or ordinary Python strategies. It describes the strategy lifecycle at a high level: create agents during initialization and invoke them during each…
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 documentation explains how a trading strategy can represent and submit orders, from basic market orders to limit, stop, stop-limit, and trailing-stop orders. It also describes a smart limit approach that moves through the bid–ask spread on a timed…
This comparison explains how Lumibot and QuantConnect LEAN differ as algorithmic trading frameworks. Lumibot is presented as a Python-first library in which strategies use ordinary Python classes, broker and data adapters, and can combine deterministic rules…
This configuration guide explains how to connect LumiBot trading strategies to Interactive Brokers, including credential setup, market data access, and paper trading. It describes storing account details in a local environment file and lists optional…
This engineering guide explains how to locate backtest slowdowns while preserving simulation behavior. It separates startup, historical data loading, strategy computation, and report generation, and recommends first distinguishing cold runs that fetch data…