"Information on Rag and Memory" matching MCP servers:

An advanced MCP server providing RAG-enabled memory through a knowledge graph with vector search capabilities, enabling intelligent information storage, semantic retrieval, and document processing.

Serves UltraRAG memory to agents over stdio MCP, providing project-local and per-user global memory. It lets agents read and append standing memory and daily dialogue rounds in UltraRAG's format, with an optional browser view.

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 high-performance memory management system for AI agents with 200+ tools including 4-tier memory architecture, advanced RAG pipeline, and Git-like versioning.

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.

Local-first memory for Claude & AI agents with hybrid search, Graph-RAG, and time-travel, runs entirely on your machine.

A local MCP server that provides persistent, project-scoped semantic memory for GitHub Copilot in VS Code, using ChromaDB and embeddings for RAG-based memory retrieval across sessions.

Enables Claude to retrieve and cite clauses from Korean national R&D manuals using RAG, grounding answers with accurate provision references.

Local RAG system for Claude Code with hybrid search (semantic + BM25), cross-encoder reranking, markdown-aware chunking, and 12 MCP tools. Zero external servers, pure ONNX in-process.

A local MCP server that gives AI assistants persistent long-term memory using a biological neural architecture with cortex, synapses, and hippocampus.

MCP server with local vector search for your codebase. Smart indexing, semantic search, Git history — all offline.

MCP server exposing memory search, index, and stats tools for agents, with honesty guards to prevent re-litigation of settled decisions.

Exposes hybrid retrieval (dense embeddings + BM25 + RRF) and document operations (search, fetch, rerank) as MCP tools, using Qdrant and OpenAI embeddings for local or server mode.

Lets AI clients store, retrieve, update, and forget long-term facts in a local SQLite database with deterministic lexical search, sharing the same memory across multiple clients without relying on model APIs or embedding services.

MCP server that integrates with LM Studio to provide a search_notes tool, allowing the chat model to retrieve and answer from a local Obsidian vault.

MyChart MCP Server

MCP server for managing project memory in AGENTS.md. Allows agents to record and remove durable facts using save/forget tools.

Exposes local memory vaults as 6 MCP tools over stdio, enabling clients like Windsurf, Zed, and Claude Desktop to read and write memory.

Hand a project over — to your next session, to Cursor/Codex/Gemini, to your successor — with the reasons attached. Local-first memory MCP for coding agents: decisions re-injected before the agent acts, drift detection across every project you run. One SQLite file, nothing leaves your machine.

An MCP server that gives AI models a persistent notebook backed by a folder of Markdown files, with tools to discover, read, write, edit, and delete notes.