mcp-memory-service and local_faiss_mcp
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 local_faiss_mcp
nonatofabio/local_faiss_mcp
Local FAISS vector store as an MCP server – Agent Memory, drop-in local semantic search for Claude / Copilot / Agents.
Implements a two-stage retrieve-and-rerank architecture using sentence-transformers for embeddings and configurable cross-encoders to improve relevance scoring. Exposes MCP tools for document ingestion (supporting PDF, TXT, MD natively plus pandoc-compatible formats) and semantic querying, alongside built-in prompts for answer extraction and summarization that integrate directly with Claude and other MCP-compatible agents.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work