tradememory-protocol vs Zengram
tradememory-protocol: TradeMemory Protocol provides a persistent memory layer for trading agents, enabling them to recall past trades with context, discover patterns, and evolve strategies autonomously. It features outcome-weighted recall, cognitive memory architecture, and an evolution engine for strategy discovery. Available as an MCP server for integration with Claude and other agents.; Zengram: Zengram is a shared memory system for multi-agent AI systems, enabling agents to store and retrieve memories across machines. It features typed memory, dual storage (Qdrant + SQLite/Postgres), multi-path search, and cross-agent capabilities like briefings and corroboration. Self-hosted, open-source, with MCP server and SDKs.
TL;DR
- Your trading agent can already execute and you want it to remember each trade with its reasoning, regime and outcome.
- You want recalled patterns weighted by outcome, with confidence, sample size and out-of-sample checks.
- You trade forex on MT5 and want trade sync.
- You take the Sharpe 3.84 result as a forecast: it is the project's own BTC backtest.
- You cannot afford LLM calls for the evolution engine, or the risk that it invents overfitted strategies.
- You are looking for an execution or broker tool: it is a memory layer.
Cross-agent memory sharing across different machines
Side-by-Side Comparison
tradememory-protocolZengramFeatures
tradememory-protocolZengramUse Cases
tradememory-protocolZengramFAQ
Deploy on DigitalOcean
Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.