tradememory-protocol
Decision audit trail + persistent memory for AI trading agents. Outcome-weighted recall, tamper-evident SHA-256 chain with RFC 3161 anchoring, 20 MCP tools.
What is tradememory-protocol?
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 of tradememory-protocol
What it is
TradeMemory is an open-source, local-first memory and brake system for AI trading agents. It pulls in your fills, identifies where your own history loses money, presents those losing trades to your agent before the next order, and can refuse an order that breaks rules you set before it reaches the broker. It uses outcome-weighted recall, a tamper-evident SHA-256 chain with RFC 3161 anchoring, and provides 20 MCP tools.
Key features
- Outcome-weighted recall: retrieves past trades weighted by outcome quality, context similarity, recency, confidence, and emotional state (OWM Framework)
- Tamper-evident SHA-256 chain with RFC 3161 anchoring for audit trail - 20 MCP tools across categories: Memory, State, Planning, Risk, Audit, Core Memory, OWM Cognitive, Risk & Governance, Evolution - Proxy brake: runs between your agent and the broker's MCP server, evaluating orders against a policy before they reach the broker - Local-first: all data stored locally, no external server required - Supports multiple venues: Hyperliquid, Alpaca, MT5, Binance
Use cases
- US equity trader: uses TradeMemory as a pre-flight checklist before every trade, syncing from Alpaca or Hyperliquid - Forex EA system: automated sync from MT5, with outcome-weighted recall for trading decisions - Audit trail: decision records with a hash chain for multi-asset compliance and review
Getting started
bash pip install tradememory-protocol # Hyperliquid: public fills, no key needed tradememory sync hyperliquid --address 0xYourAddress # Alpaca: read-only calls with your own keys, kept in a local file tradememory sync alpaca --env-file ~/.secrets/alpaca.env Add to Claude Desktop (claude_desktop_config.json): json { “mcpServers”: { “tradememory”: { “command”: “uvx”, “args”: [“tradememory-protocol”] } } } For proxy brake: bash pip install “tradememory-protocol[proxy]” # Python 3.12+ tradememory proxy init --account-id --symbols AAPL,MSFT tradememory proxy doctor --env-file ~/.secrets/alpaca-paper.env tradememory proxy config
License and pricing
MIT license. Open source.
Based on the project's public README and repository metadata.
