"Vault" matching MCP servers:

Enables AI agents to persist and retrieve structured memory across sessions and models via MCP tools for cataloging, searching, and saving facts, with automatic supersession and scope filtering.

MCP server providing persistent memory for AI applications, enabling Claude to store and recall memories with hybrid search and knowledge graph.

RAG Vault lets your AI coding assistant search your private documents locally. Everything runs on your machine and your data stays private.

Mimir is Perseus's external persistent memory backend — a lightweight Rust MCP server that stores cross-session facts so agents remember what they learned last week. Zero network calls, no API keys, just SQLite + FTS5 running alongside your workspace.

A self-hostable semantic skill registry for AI agents, providing searchable, versioned, and verified skills over a single MCP endpoint with per-agent private vaults and trust tiers.

Local-first agentic knowledge layer over Obsidian notes, enabling MCP-aware agents to search, retrieve, and compile knowledge with provenance and task contracts.

Enables hybrid search, reading, writing, and managing a local Obsidian vault through MCP tools and a REST API, including section patching, appending, moving notes with link rewriting, and frontmatter updates.

Enables offline archiving, deduplication, and quality-controlled indexing of Medium articles, exposing MCP tools for retrieving, managing, and exporting knowledge for AI agents and local pipelines.

Lets Claude Code and Claude Desktop retrieve and explore an Obsidian vault through tools for semantic search, reading notes, following graph neighbors, and listing topics.

Enables private, self-hosted storage and semantic/full-text retrieval of durable facts extracted from conversations, with provenance, corrections, conflict records, and scoped bearer authentication.

Enables local-first, offline hybrid retrieval from Markdown notes, MinerU papers, and code via MCP, with BM25 keyword and local vector search, outline-aware chunking, PDF twin-binding, and incremental file watching.

Enables local-first, source-cited AI answers about your TTRPG campaign lore from your own documents, usable in Discord, Foundry VTT, or any MCP client while refusing to invent information outside your sources.

Enables semantic and full-text search over markdown notes, with tools to create, edit, move, and delete notes, all through MCP. Runs entirely locally using Ollama for embeddings and SQLite for storage, working with Obsidian or standalone.

Serves as a unified MCP gateway to an Obsidian vault, enabling AI agents to perform hybrid lexical/vectorial semantic search, explore note graphs, and write through consent-based intent batches with conflict detection.

An encrypted, local-first memory server for AI agents that uses SQLite + FTS5 hybrid search, keeping memory off the GPU to maximize HBM for inference.

MCP server for semantic search in an Obsidian Second Brain vault using self-hosted Qdrant and Google Gemini embeddings.

A read-only MCP server that enables semantic search and retrieval over a local Markdown knowledge base with heading-aware chunking and multilingual embeddings.

Enables local hybrid search over Obsidian and Markdown vaults via MCP, combining vector retrieval, full-text search, reranking, graph navigation, and safe CRUD while keeping data local.

MCP server for hybrid retrieval over markdown vaults, combining sqlite-vec embeddings and FTS5 keywords with reciprocal rank fusion, plus optional cross-encoder reranking.

Provides persistent OKF memory for DeepSeek Harness by storing and indexing Markdown memories in SQLite FTS5, enabling agents to search, store, and export memories through MCP tools.