by mnemox-ai · MCP Server · ★ 891
TradeMemory Protocol A Mnemox Project — MCP server that gives AI trading agents persistent, outcome-weighted memory. Works with: Claude Desktop · Claude Code · Cursor · Windsurf · any MCP client The Problem Your AI trading agent has no memory. Every session starts from zero — same mistakes, same blown setups, no learning. The Fix Session 1: Agent loses $200 → remembertrade stores context + outcome Session 2: Agent calls recallmemories → "Asian breakouts: 0% win rate, -$590" Agent
| Stars | 891 |
| Forks | 117 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 57.27/100 |
| Open Issues | 1 |
| Last Updated | 2026-05-14 |
| Created | 2026-02-23 |
| Platforms | claude-code, mcp, python |
| Est. Tokens | ~435k |
Explore other popular mcp server tools:
tradememory-protocol is Decision audit trail + persistent memory for AI trading agents. Outcome-weighted recall, SHA-256 tamper detection, 17 MCP tools.. It is categorized as a MCP Server with 891 GitHub stars.
tradememory-protocol is primarily written in Python. It covers topics such as ai-agents, claude, crypto.
You can find installation instructions and usage details in the tradememory-protocol GitHub repository at github.com/mnemox-ai/tradememory-protocol. The project has 891 stars and 117 forks, indicating an active community.
tradememory-protocol is released under the MIT license, making it free to use and modify according to the license terms.