MCP servers for long-term memory and vector search: store notes, embeddings and facts so an AI assistant remembers across sessions. 799 servers in dieser Kategorie.
Füge das GitHub Repo ein und wir listen ihn nach einem kurzen Review auf.
Server einreichen
Provides a local-first persistent memory layer that allows different AI agents to share project-specific knowledge and work journals.
$claude mcp add ai-agent-memory-mcp -- uvx ai-agent-memory-mcp
Provides a tiered, Markdown-backed hybrid memory system for AI agents with decision tracking and multi-tenancy support.
Provides AI coding agents with a persistent, local, repository-aware memory layer using SQLite to store project rules, corrections, and architectural decisions.
$claude mcp add repo-memory-mcp -- uvx repo-memory-mcp-ai
Lets AI agents on multiple machines share a synced, searchable memory journal without a central server.
Enables AI clients to perform local vector storage, document ingestion, and semantic search using FAISS for Retrieval-Augmented Generation.
$claude mcp add local-faiss-mcp -- uvx local-faiss-mcp
Gives AI clients and IDEs a persistent shared memory layer to save, search, and retrieve documents and facts across sessions.
$claude mcp add --transport http memwyre https://server.memwyre.tech/mcp/
Provides a local-first memory infrastructure for AI agents using hybrid vector, lexical, and graph retrieval.
Provides AI agents with a persistent, graph-based long-term memory framework using SQLite or Neo4j to store entities, observations, and relationships.
Provides a self-hosted, two-tier knowledge graph memory for AI agents using Graphiti and FalkorDB over a private Tailscale network.
Provides a memory engine for AI agents featuring vector search, knowledge graphs, and hybrid retrieval.
Provides persistent long-term memory for Claude Code and MCP clients using hybrid BM25, vector, and knowledge-graph search over Markdown files.
Provides shared project memory for AI agents with source-backed facts, reviewable updates, and verifiable citations.
Provides persistent, shared memory for AI agents using a plain-markdown Obsidian vault with hybrid search and a browsable knowledge graph.
Provides local-first neural memory for AI agents by indexing Markdown vaults with lexical, semantic, and knowledge-graph search capabilities.
Provides user-owned, cross-agent AI memory using a local SQLite database and Gemini embeddings to enable persistent context across different AI clients.
Provides a persistent, local, CPU-only memory system for AI agents using hybrid retrieval and automated consolidation.
Provides embedded, local-first memory and hybrid retrieval for AI agents using a single SQLite file.
$claude mcp add rmbr -- uvx rmbr
Provides a bi-temporal knowledge graph and token-budgeted context compiler to give AI coding agents persistent, conflict-aware memory.
Provides AI agents with persistent memory using hybrid vector search, full-text retrieval, and a knowledge graph backed by PostgreSQL.
Provides persistent SQLite-based episodic memory and semantic knowledge graphs to give AI agents cross-session recall and context.