"Hybrid Memory Models Combining Relational, Graph, and RAG Approaches" matching MCP servers:

Enables AI agents to use a hybrid dense+sparse RAG system with tag-based long-term memory (importance, knowledge-type decay, access-frequency boost) via MCP tools for document ingestion, hybrid search, staged reranking, forgetting, and index management.

An MCP server that provides a search_docs tool with hybrid retrieval (BM25 + dense vectors) and cross-encoder reranking, backed by evaluation, prompt-injection guardrails, and OpenTelemetry tracing.

Enables question answering over technical documents (Markdown, TXT, PDF) using hybrid retrieval (vector + lexical) with cited sources and audit logging, fully locally with optional cloud fallback.

Enables hybrid retrieval-augmented generation with semantic and keyword search over documents, supporting multiple formats and providing MCP integration for Claude Desktop.

Enables Claude to perform hybrid search across local documents by combining semantic vector retrieval and BM25 keyword matching for optimal context recovery. It supports multiple file formats including PDF, CSV, and Markdown, leveraging local Ollama models for private and efficient document querying.

Universal FastMCP bridge into a hybrid memory stack, enabling MCP-capable agents to save, search, read, and recall memories using OpenViking and Honcho backends.

Enables hybrid search and agentic retrieval over Confluence pages via MCP tools, allowing Claude Desktop, Cursor, or Claude Code to search and retrieve Confluence content.

A modular Retrieval-Augmented Generation (RAG) framework that provides hybrid search and knowledge retrieval capabilities via the Model Context Protocol. It enables users to integrate document-based knowledge into LLM workflows with support for dense/sparse retrieval, reranking, and observability.

Enables natural-language and keyword search across Obsidian notes, returning reranked passages with provenance, and supports reading notes and incremental indexing.

Enables persistent, intelligent memory across sessions using a weighted, interconnected graph that evolves through conversation.

RAG Knowledge Graph - MCP server providing AI-powered tools and automation by MEOK AI Labs

A context-aware memory MCP server with authority weighting, conflict detection, and typed relationship edges for intelligent memory retrieval.

Enables Claude to recall and query past conversations through a local knowledge graph and vector index, with tools for searching memory, retrieving related entities, and adding new memories.

Enables AI agents to build and query a persistent knowledge graph with entities, relationships, and observations. Features a core index system that ensures critical information is always accessible across all memory operations.

Enables natural language search over PDF documents using vector search, allowing MCP clients like Claude Desktop to query PDF content.

A local MCP server enabling hybrid search over documents, memory, and knowledge graphs for retrieval-augmented generation, with tools for SQLite, semantic memory, and entity-relationship queries.

Enables persistent project memory for Hermes Agent by storing and retrieving wiki, code, and learning layers locally, with tools to recall, learn, retire, and ingest information beyond the context window.

A thin MCP client that provides a search_kb tool for querying a remote oG-Memory knowledge base, enabling any agent to retrieve relevant information without local setup.

A local-first Graph-RAG system combining ChromaDB with metadata-based graph relationships and Gemini 2.5 Flash for intelligent Q&A over Obsidian vaults, supporting MCP clients like Claude Desktop, Cursor, and Raycast.

Provides a dynamic SQLite-backed code knowledge graph for AI assistants, with MCP tools to inspect symbols, find dependency paths, and analyze code structure across multiple languages.