trader-memory-core

Track investment theses across their lifecycle by registering the initial thesis, attaching position sizing data, and generating a postmortem report with P&L and MAE/MFE analysis after exiting the position. This provides a persistent state layer for analyzing investment decisions and outcomes.

Postmortem analysis is the process of reviewing closed investment theses to calculate P&L and MAE/MFE metrics. You need it after exiting a position to evaluate your investment decisions, understand maximum adverse excursion, and refine future trading strategies.

Yes, you need an FMP API key for postmortem calculations. The Skill requires Python and additional dependencies including pyyaml, requests, jsonschema, and the fmp_price_adapter to ingest data and manage position sizing.

Yes, you can register a new investment thesis for a specific stock like AAPL. Use the 'register thesis' command to input the ticker, manage its lifecycle, and attach position sizing data to track performance over time.

Manage position sizing data by attaching it directly to registered investment theses within a persistent state layer. This allows you to track multiple theses simultaneously, review their performance, and execute comprehensive postmortem analysis upon position exit.

A dedicated thesis tracking system provides a persistent state layer that automates data ingestion, position sizing, and P&L calculations. Unlike spreadsheets, it enforces a structured lifecycle from idea generation to postmortem analysis, ensuring consistent MAE/MFE evaluation.