Gives trading agents persistent memory that learns from outcomes. Records every trade decision with reasoning, confidence, and market context, then uses outcome-weighted recall across five memory types to surface relevant past experiences. Detects behavioral biases like overtrading and revenge trading, provides Kelly-criterion position sizing from recalled outcomes, and generates strategy adjustments based on discovered patterns.

Source

Repository: https://github.com/mnemox-ai/tradememory-protocol

Maintain TradeMemory?

Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.

[![TradeMemory on getagentictools](https://getagentictools.com/badge/mcp/mnemox-ai-tradememory-protocol.svg)](https://getagentictools.com/mcp/mnemox-ai-tradememory-protocol?ref=badge)

Source

Maintain TradeMemory?

Related mcp