"Integrating Obsidian with ChromaDB for Memory Management" matching MCP servers:

Stores AI memories as Markdown files for visualization in Obsidian's graph view, allowing users to create knowledge graphs with entities, relations, and observations.

Enables AI harnesses to maintain a persistent memory layer backed by a local SQLite file, providing MCP tools to add, search, deprecate, and synchronize facts without deleting history.

MCP server for Obsidian vaults, optimised for Cursor agents — safe note editing, lean tool surface, direct filesystem access.

Provides AI coding assistants persistent engineering memory stored as Markdown files in an Obsidian vault, enabling project context retrieval, session capture, decision recording, and memory search without requiring Obsidian to be running.

Turns a codebase into a persistent knowledge graph so AI coding agents can answer structural questions about functions, call chains, routes, and cross-service links through graph queries instead of reading files one by one.

A hybrid MCP server that bridges Claude Desktop with both Obsidian vaults and the Bonfires platform, enabling seamless knowledge management and collaboration.

A self-hosted MCP server with a management UI for reading, searching, editing, and organizing notes in an Obsidian vault, with OAuth and token authentication, git snapshots, and optional Obsidian Sync.

Persistent semantic memory server for Obsidian vaults, enabling AI agents to search, read, write, and explore notes with semantic understanding and incremental indexing.

This is a connector to allow Claude Desktop (or any MCP client) to read and search any directory containing Markdown notes (such as an Obsidian vault).

Enables LLMs to read, search, and manage Obsidian vault markdown files, including YAML frontmatter, wikilinks, and graph operations through a secure stateless I/O layer.

Enables local read-first access to an Obsidian vault through the Obsidian Local REST API, letting MCP clients retrieve notes, search, list tags, and inspect document structure while keeping API key and data on-device.

Persists Claude Code sessions to Notion as team memory, enabling queryable recall of decisions, work state, and project architecture.

Enables semantic search across Obsidian vaults using vector embeddings and ChromaDB. Supports multiple vaults with real-time indexing and provides both MCP server and CLI interfaces for natural language querying of notes.

Auto-captured, auto-recalled, path-scoped memory for AI coding agents and teams.

Slipstream - Built by Vektor Memory - a persistent multi-layered memory architecture. 4-layer associative graph memory (MAGMA) with autonomous REM cycle, CLI, DXT-MCP Cloak Tools.

Enables AI assistants to interact with local Obsidian vaults through direct filesystem access for reading, creating, and managing notes. It features high-performance SQLite indexing for fast searches, regex support, and tools for organizing tags and links without requiring additional plugins.

Model-agnostic, agent-ready Obsidian MCP server with RBAC, SLSA provenance, and native search. 163 tools across 31 domains, multi-vault, pluggable embeddings.

A standalone Node MCP server that provides semantic search, knowledge graph, and vault editing over an Obsidian vault. It runs locally as a single stdio process without requiring an Obsidian plugin for core functionality.

Enables AI coding agents to read, write, search, and organize notes in an Obsidian vault directly via the filesystem.

This MCP server enables Claude to interact with an Obsidian vault for persistent, structured memory, providing tools for note creation, semantic search, graph traversal, and session memory.