Tradememory
Skill Verified ActiveAI trading memory with outcome-weighted recall and autonomous strategy evolution. 17 MCP tools, 1,233 tests, works with any trading platform.
To equip AI trading agents with persistent memory, enabling them to learn from past trades, recall relevant information, and autonomously evolve new trading strategies.
Features
- Outcome-weighted memory recall
- LLM-powered autonomous strategy evolution
- SHA-256 tamper-proof trading decision records
- Platform-agnostic trade data integration
- 17 comprehensive MCP tools for memory and evolution
Use Cases
- Recording and recalling trade history with outcome-weighted scoring
- Discovering new trading patterns and strategies from raw price data
- Analyzing behavioral patterns and agent state (confidence, drawdown)
- Generating and verifying tamper-proof audit trails for regulatory compliance
Non-Goals
- Executing trades or managing user funds
- Directly interacting with trading platforms (requires separate sync scripts)
- Replacing core AI agent decision-making capabilities
Installation
npx skills add mnemox-ai/tradememory-protocolRuns the Vercel skills CLI (skills.sh) via npx — needs Node.js locally and at least one installed skills-compatible agent (Claude Code, Cursor, Codex, …). Assumes the repo follows the agentskills.io format.
Quality Score
VerifiedTrust Signals
Similar Extensions
Trading Memory
100Domain knowledge for AI trading memory — Outcome-Weighted Memory (OWM) architecture, 5 memory types, recall scoring, and behavioral analysis. Use when recording trades, recalling similar contexts, analyzing performance, or checking behavioral drift. Triggers on "record trade", "remember trade", "recall", "similar trades", "performance", "behavioral", "disposition", "affective state", "confidence".
Trader Regime
100Detect current market regime using npx neural-trader — bull/bear/ranging/volatile classification with recommended strategy
TradeMemory Protocol
100Domain knowledge for the Evolution Engine — LLM-powered autonomous strategy discovery from raw OHLCV data. Covers the generate-backtest-select-evolve loop, vectorized backtesting, out-of-sample validation, and strategy graduation. Use when discovering trading patterns, running backtests, evolving strategies, or reviewing evolution logs. Triggers on "evolve", "discover patterns", "backtest", "evolution", "strategy generation", "candidate strategy".
Risk Management
100Risk management domain knowledge for trading agents — affective state monitoring, position sizing, drawdown management, tilt detection, and behavioral guardrails. Use when checking risk before trades, managing drawdowns, detecting behavioral drift, or enforcing discipline. Triggers on "risk", "drawdown", "tilt", "position size", "lot size", "confidence", "revenge trading", "overtrading", "discipline".
Forecast Scenarios
100Model best-case, worst-case, and likely revenue scenarios with sensitivity analysis for strategic planning. Use when: building financial forecasts; presenting board scenarios; planning headcount around revenue uncertainty; modeling pricing changes impact; preparing investor updates with upside/downside ranges
Agentdb Memory Patterns
99Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.