mcp-memory-service and tradememory-protocol
The `mnemox-ai/tradememory-protocol` is an ecosystem sibling to `doobidoo/mcp-memory-service`, as it implements a specific use case—AI trading memory—as an MCP server, indicating it's a specialized application or extension of the MCP protocol facilitated by the `mcp-memory-service`.
About mcp-memory-service
doobidoo/mcp-memory-service
Open-source persistent memory for AI agent pipelines (LangGraph, CrewAI, AutoGen) and Claude. REST API + knowledge graph + autonomous consolidation.
Consolidates multi-agent memory using a knowledge graph with typed edges (causes, fixes, contradicts) and autonomous compression, accessible via REST API with ONNX-based embeddings that run locally. Implements Remote MCP support for browser-based claude.ai integration via Server-Sent Events, alongside traditional desktop MCP, with OAuth 2.0 authentication and self-hosted infrastructure (no cloud lock-in). Agent identity is tracked via `X-Agent-ID` headers for scoped retrieval, and conversation threading is preserved through `conversation_id` fields, enabling both shared memory across agent fleets and inter-agent messaging through semantic tag-based filtering.
About tradememory-protocol
mnemox-ai/tradememory-protocol
MCP server for AI trading memory — outcome-weighted cognitive memory with 10 tools, 399 tests.
Implements outcome-weighted memory across three cognitive layers (L1 episodic → L2 semantic → L3 procedural) inspired by ACT-R, where past trades are recalled by similarity and ranked by performance—enabling strategy discovery via the Evolution Engine. Includes 17 MCP tools, tamper-proof audit trails (SHA-256 hashing), and statistical validation (Deflated Sharpe Ratio walk-forward testing) for regulatory compliance with MiFID II and EU AI Act. Integrates with MT5, Binance, Alpaca, and other brokers while supporting Claude Desktop, Cursor, VS Code, and Docker deployments.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work