tradememory

name	tradememory
slug	tradememory
version	0.5.1
description	AI trading memory with outcome-weighted recall and autonomous strategy evolution. 17 MCP tools, 1,233 tests, works with any trading platform.
source	https://github.com/mnemox-ai/tradememory-protocol
repository	https://github.com/mnemox-ai/tradememory-protocol
homepage	https://github.com/mnemox-ai/tradememory-protocol
metadata	{"openclaw":{"emoji":"📊","category":"finance","requires":{"bins":"[Truncated]","env":"[Truncated]"},"os":["linux","darwin","win32"],"homepage":"https://github.com/mnemox-ai/tradememory-protocol"}}

TradeMemory Protocol

Give your AI agent persistent trading memory. TradeMemory records every trade, recalls past decisions weighted by outcome quality, discovers behavioral patterns, and autonomously evolves new strategies from raw price data.

Outcome-Weighted Memory (OWM) — 5 memory types (episodic, semantic, procedural, affective, prospective) that score recall by P&L outcome, context similarity, recency, and confidence. Winning trades surface first.

Evolution Engine — LLM-powered strategy discovery. Feed it OHLCV data from any exchange, it generates candidate patterns, backtests them vectorized, validates out-of-sample, and graduates survivors. No manual rule writing.

Platform-agnostic — works with MT5, Binance, Alpaca, or any broker that outputs trade data. 1,233 tests passing. MIT licensed.

Installation

pip install tradememory-protocol

Verify:

python -c "import tradememory; print('TradeMemory ready')"

Setup

Claude Desktop (via uvx)

Add to your Claude Desktop MCP config:

{
  "mcpServers": {
    "tradememory": {
      "command": "uvx",
      "args": ["tradememory-protocol"]
    }
  }
}

Claude Code

claude mcp add tradememory -- uvx tradememory-protocol

Manual (local server)

python -m tradememory

Runs the MCP server on stdio. For the REST API server:

python -m tradememory.server
# Runs on http://localhost:8000

MCP Tools Reference

Core Memory (2 tools)