Enterprise DNA
M MCP Servers Developer low

mnemox-ai/tradememory-protocol

by Various

Decision audit trail + persistent memory for AI trading agents. Outcome-weighted recall, SHA-256 tamper detection, 17 MCP tools.

M

MCP

mnemox-ai/tradememory-protocol

Added 1 June 2026

#ai-agents #claude #crypto #evolution-engine #forex #mcp #mcp-server #memory

Overview

An open-source Python library that provides a decision audit trail and persistent memory for AI trading agents. It uses outcome-weighted recall to prioritize past decisions and SHA-256 hashing for tamper detection. The library includes 17 MCP tools for integration.

Best for

Best for
Developers building AI trading agents that need auditable, persistent memory

Use cases

  • Auditing trading agent decisions with tamper-evident logs
  • Persisting agent memory across trading sessions
  • Improving decision recall by weighting outcomes

Notes

An open-source Python library that provides a decision audit trail and persistent memory for AI trading agents. It uses outcome-weighted recall to prioritize past decisions and SHA-256 hashing for tamper detection. The library includes 17 MCP tools for integration.

1,082 stars on GitHub. Last updated 2026-06-01. Licensed MIT.

Use cases

  • Auditing trading agent decisions with tamper-evident logs
  • Persisting agent memory across trading sessions
  • Improving decision recall by weighting outcomes

Pros

  • Tamper detection via SHA-256 hashing ensures audit integrity
  • Outcome-weighted recall helps agents learn from past results
  • Open source with 1,082 stars and active community

Cons

  • Limited to trading agent use cases
  • Requires integration with existing agent frameworks
  • Dependency on MCP tools may add setup complexity

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.

Pros

  • Tamper detection via SHA-256 hashing ensures audit integrity
  • Outcome-weighted recall helps agents learn from past results
  • Open source with 1,082 stars and active community

Cons

  • Limited to trading agent use cases
  • Requires integration with existing agent frameworks
  • Dependency on MCP tools may add setup complexity