by mnemox-ai
Memory layer for AI trading agents. Outcome-weighted recall, autonomous strategy evolution, 15 MCP tools.
# Add to your Claude Code skills
git clone https://github.com/mnemox-ai/tradememory-protocolWhat if your trading bot could learn from every mistake — and invent better strategies by itself?
200+ trading MCP servers execute trades. None of them remember what happened.
TradeMemory is the memory layer that changes that.
</div>"Why does my bot keep making the same mistakes?"
Persistent memory records every trade with full context — entry reasoning, market regime, confidence level, outcome. Pattern discovery finds what you can't see manually.
"My strategy worked for months, then suddenly stopped."
<details> <summary>Claude Code / Cursor / Other MCP clients</summary>No comments yet. Be the first to share your thoughts!
Outcome-weighted recall auto-downweights patterns from old regimes. Your bot adapts without you rewriting a single rule.
"How do I know it's not just overfitting?"
Every pattern carries Bayesian confidence + sample size. Built-in out-of-sample validation. Suspicious patterns get flagged, not blindly followed.
"I just want it to figure out what works."
Evolution Engine: feed raw price data. No indicators, no hand-written rules. It discovers, backtests, eliminates, and evolves — autonomously.
22 months of BTC data. Sharpe 3.84. 477 trades. 91% positive months. Zero human strategy input.
pip install tradememory-protocol
Add to your Claude Desktop config (claude_desktop_config.json):
{
"mcpServers": {
"tradememory": {
"command": "uvx",
"args": ["tradememory-protocol"]
}
}
}
Then say to Claude:
"Record my BTCUSDT long at 71,000 — momentum breakout, high confidence."
Claude Code:
claude mcp add tradememory -- uvx tradememory-protocol
Cursor / Windsurf / any MCP client — add to your MCP config...