tradememory

Level ALocal

Decision audit trail + persistent memory for AI trading agents. Outcome-weighted recall, tamper-evident SHA-256 chain with RFC 3161 anchoring, 20 MCP tools.

Overview

TradeMemory is an open-source, local-first memory and guardrail layer for AI trading agents. It imports your fills, surfaces where your own history lost money, puts those losing trades in front of the agent before the next order, and can refuse orders that break rules you set. Every decision is recorded in a SHA-256 hash chain with RFC 3161 anchoring, exposed through 20 MCP tools for memory, state, planning, risk, and audit.

⭐ 1.4kOffice & ProductivityPythonRepo ↗Updated 2026-10-23

Installation

MCP client config (paste into mcp.json)

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

Agent install prompt

Copy and paste into Cursor / Claude / other agents to install this MCP for you

Please read this MCP repository and install it into my current environment:
https://github.com/mnemox-ai/tradememory-protocol/tree/master/src/tradememory

Known working client config (can write into mcp.json):
{
  "mcpServers": {
    "tradememory-protocol": {
      "command": "uvx",
      "args": [
        "tradememory-protocol"
      ]
    }
  }
}

Please: 1) check README for deps and env vars; 2) write config for my client; 3) if secrets are missing, tell me what to fill — do not invent values.

Related servers