Skip to main content
Glama

remember_trade

Store trading data with automatic updates to episodic, semantic, procedural, and affective memory layers for performance analysis and strategy improvement.

Instructions

Store a trade into OWM multi-layer memory with automatic updates.

Writes to episodic memory and automatically updates semantic (Bayesian), procedural (running averages), and affective (EWMA confidence/streaks). Also writes to trade_records for backward compatibility.

Args: symbol: Trading instrument (e.g. "XAUUSD") direction: "long" or "short" entry_price: Entry price of the trade exit_price: Exit price of the trade pnl: Profit/loss in account currency strategy_name: Strategy used (e.g. "VolBreakout") market_context: Description of market conditions pnl_r: P&L as R-multiple (risk units). Improves OWM scoring quality. context_regime: Market regime (trending_up/trending_down/ranging/volatile) context_atr_d1: ATR(14) on D1 in dollars confidence: Agent confidence level 0-1 (default 0.5) reflection: Lessons learned from this trade max_adverse_excursion: Maximum adverse excursion during the trade trade_id: Optional custom ID. Auto-generated if omitted. timestamp: ISO format timestamp. Defaults to now (UTC).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
symbolYes
directionYes
entry_priceYes
exit_priceYes
pnlYes
strategy_nameYes
market_contextYes
pnl_rNo
context_regimeNo
context_atr_d1No
confidenceNo
reflectionNo
max_adverse_excursionNo
trade_idNo
timestampNo

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/mnemox-ai/tradememory-protocol'

If you have feedback or need assistance with the MCP directory API, please join our Discord server