"The Guardian" matching MCP servers:

Provides OpenCode with adaptive long-term memory by storing preferences, lessons, and usage history locally in SQLite, enabling AI to remember and adapt to users through context-based learning.

Connects AI assistants directly to Obsidian vaults with intelligent note creation using templates, semantic search, smart tagging to avoid duplicates, and specialized agent roles (Guardian, Researcher, Connection Weaver) for managing knowledge bases.

Hosted MCP gateway to the RTP global commons of neighborhood practice and relational tech knowledge. AI builders can query 275+ recipes, frameworks, and methodology docs for community organizing.

An MCP server that provides AI tools with relational tech principles, patterns, and the Studio library to guide builders in creating community-centered tools using embedded design.

A high-performance persistent memory layer for AI agents with multi-modal support, 47 retrieval channels, and 50-tier guardian chains, integrating 12+ memory approaches into a unified architecture.

Local-first MCP server that enables multiple Claude agents to coordinate through a shared message bus with SQLite persistence and real-time clock anchoring.

A focused project memory system that provides knowledge graph capabilities and SQLite database operations for intelligent entity tracking and workflow management. It enables AI models to maintain persistent project context through 17 specialized tools, 10 resources, and 27 pre-built prompts.

An MCP server that manages your conversation context automatically, pruning dead branches and keeping an audit trail of every cut.

Enables context-aware household safety workflows to coordinate smart-home events, household context, policies, risk, and safe actions through auditable MCP tools for status, event evaluation, wellness checks, rule creation, and action requests.

The open-source, self-organizing memory for all your AI tools. Persistent memory over MCP (remember, recall, observe): background agents extract entities, resolve conflicts, and keep cited syntheses current in an append-only, encrypted, single-tenant vault.

Cortex is a Claude Code plugin that gives Claude persistent memory across sessions. A background miner extracts durable lessons (decisions, conventions, bug fixes, preferences) from your completed sessions, stores them as markdown in an Obsidian vault, and automatically surfaces relevant ones at the start of each new session via a query-tailored briefing.

Indexes the session histories Claude Code, Codex CLI and opencode already write into a local searchable memory. MCP recall tools, session-start auto-recall, secret redaction at index time, cross-machine sync over SSH.

This MCP server provides tools to search for songs, artists, and random records from the Bide & Musique catalogue. It offers read-only access to tens of thousands of French songs with no authentication needed.

Local-first memory for coding agents. Discovers the memory, instructions, and rules Claude Code, Codex, and Cursor already wrote on your machine, combines them into one canonical Markdown tree, and serves grounded, cited recall through tools like ask_memory and canonical_memory.

Procedural memory for coding agents: not facts about the user, but how a task was solved — trigger, steps, outcome, lessons. Hooks recall it automatically; skills strengthen only on outside evidence and unused ones decay. Each memory carries its provenance and only the owner approves one as a rule. Local SQLite + FTS5, no API key, no cloud. One database for Claude Code, Codex and Cursor.

Lets AI assistants understand what you're working on — current screen content, recent dictation, clipboard, and saved notes — running entirely on your own machine with nothing sent to the cloud.

Persistent semantic memory for your SQL databases. The name is ironic — it remembers everything.

Collective memory for AI agents. One agent solves a bug - every agent in the world gets the fix instantly.

Flatten Claude Code sessions: keep every prompt and event verbatim, resume at a lower token count. An MCP server.

MCP server for the full Pāli Tipiṭaka — ~444,000 segments at parity with SuttaCentral (Sutta + Vinaya + Abhidhamma). Hybrid search, full-sutta fetch with cross-references, segment-aligned translation comparison, and Pāli word lookup. Offered as Dhamma Dāna.