Search hierarchical memory using hybrid ranking to retrieve facts prioritized by user, team, and org precedence.
Apache 2.0
306,570 tools. Last updated 2026-07-25 14:25
"Hybrid Memory Models Combining Relational, Graph, and RAG Approaches" matching MCP tools:
- Search indexed memories with hybrid recall, combining BM25, semantic, graph, and temporal retrievers for ranked results.Apache 2.0
- Find related memories by combining knowledge graph traversal with semantic similarity, enabling discovery of associations between memory entries.MIT
- Perform hybrid web searches combining broad coverage with technical documentation focus. Choose between general web search or documentation-optimized mode to get relevant results with titles, URLs, and snippets.
- Remove data from memory by targeting a specific dataset or clearing all stored information from relational, graph, and vector databases.Apache 2.0
- Sync vector store data to relational tables, making relational queries up to date after document ingestion. Idempotent operation.MIT
Matching MCP Servers
- Flicense-qualityBmaintenanceUniversal FastMCP bridge into a hybrid memory stack, enabling MCP-capable agents to save, search, read, and recall memories using OpenViking and Honcho backends.Last updated
- AlicenseAqualityAmaintenanceSelf-hosted personal knowledge graph for Claude that persists across sessions, devices, and tools. Built on Neo4j with local semantic embeddings; OAuth 2.1 lets Claude Code, Claude Desktop, and claude.ai web all hit the same graph.Last updated23622MIT
Matching MCP Connectors
The Graph MCP — indexed blockchain data via subgraph GraphQL queries
Persistent long-term memory for AI agents: semantic search, knowledge graph, and task canvas.
- Search your personal knowledge vault using hybrid retrieval that combines semantic search, keyword matching, and knowledge graph traversal. Returns cited passages from your notes.MIT
- Retrieve relevant information from persistent memory by combining vector search, full-text search, and knowledge graph enrichment for AI coding agents.MIT
- Retrieve a focused subgraph of memories to answer a question, avoiding context flooding by walking the graph from hybrid search results within a token budget.PolyForm Noncommercial 1.0.0
- Export the memory graph to an interactive HTML file for visual inspection. Returns the output path and graph counts.Apache 2.0
- Retrieve relevant information from RAG and Wiki sources using keyword, semantic, hybrid, or auto search strategies.MIT
- Search a repository using Graph RAG hybrid retrieval (semantic, keyword, and graph diffusion) to return relevant code chunks and relationship edges for code evidence collection.MIT
- Analyze monetization strategies including free, subscription, credits, and hybrid models to determine optimal approaches for your project.MIT
- Creates or updates a node in a persistent graph memory for long-term RAG retrieval. Requires initialized NFT matrix; if missing, purchase license key first.Business Source 1.1
- Search memory files using hybrid, lexical, or vector methods to retrieve relevant information from stored data.MIT
- List running models to display which models are currently loaded in memory.AGPL 3.0
- Convert skill directories into Weaviate-ready format for hybrid vector and keyword search. Enables production RAG applications with BM25 and vector retrieval.MIT
- Search your personal knowledge graph using hybrid search to find relevant thoughts, filter sources, and explore connections.MIT
- Build a relationship graph across specified models, returning edges and optional Mermaid ER diagram.MIT
- Update entities by adding observations to their data in the Elasticsearch Knowledge Graph, enhancing the memory-like storage and retrieval for AI models.MIT