Memory MCP Servers — Page 2

Local-first AI knowledge base and LLM wiki with source-cited pages and MCP access for coding agents.

Complete 78-card tarot meanings, random draws, spreads and yes-or-no readings for AI assistants.

A local MCP (Model Context Protocol) server for portable, long-term agentic memory, a thumb drive for your AI context.

Your AI remembers now. Persistent brain that compounds across every session, every tool. Memories auto-link by tags. Free.

Self-hosted MCP server giving AI agents persistent memory — Markdown source of truth, hybrid BM25+embedding search, typed graph relations.

Fully offline, encrypted-at-rest memory for AI agents, with the embedding vectors encrypted too, exact RAM-resident search, crypto-shred deletion and a hash-chained audit log.

Free, no-signup persistent memory for AI agents over MCP — remember/recall facts across sessions with one hosted URL. Zero setup, no API key.

Persistent memory for AI agents over MCP: local-first storage, negative learning from past failures, and hybrid recall, published on npm as wyrm-mcp.

Local stdio MCP server for coding agents: shared troubleshooting memory, agent-to-agent help posts, replies, and a unified inbox. Quick start: npx -y agent-only-mcp

Memory that forgets. A persistent, self-revising belief state for agentic R&D. Prunes dead branches and deduces answers without spending probes.

Cross-vendor AI memory over MCP. One semantic memory store, readable and writeable from every MCP client — Claude, ChatGPT, Cursor, Windsurf, Zed, Kimi.

@memofs/mcp-server lets AI coding agents securely read and write MemoFS memory through standard Model Context Protocol tools.

Persistent visual cache for LLM-driven software development. Caches screenshots using perceptual hashing, vector search, and AX trees to prevent token overhead and visual hallucination loops.

Persistent, branch-aware workflow state memory MCP server for AI coding assistants. Tracks tasks, accepted decisions, and active blockers to prevent session context bloat and speed up development.

toon-memory es un servidor MCP de memoria persistente 100% local diseñado para asistentes de código con IA (Cursor, Claude Code, Windsurf, etc.). Utiliza el formato ultraeficiente TOON para reducir el consumo de tokens hasta en un 30%, permitiendo a los agentes guardar, buscar y consolidar el contexto y las decisiones del proyecto entre sesiones de forma privada y cifrada (AES-256).

A local-first, generic memory layer for MCP agents, with multilingual hybrid search and reranking, versioned memories, provenance, temporal recall, relationships, feedback, and secure multi-agent spaces.

Local-first structured project memory for AI coding agents. Requires the free Wuniq desktop app.

Lightweight, High-Performance Go-Based MCP Shared Memory Bank for Cross-Agent Collaboration

Privacy-first local memory vault every AI shares over MCP. Markdown + SQLite on your machine; Claude, ChatGPT, Cursor, and any MCP client read and write it live. No cloud, no account, no telemetry.

Persistent semantic memory that compounds across sessions, plus a judgment ledger with real calibration (Brier scores, bias maps).

Local LLM chat history served over MCP. Embedded Postgres + pgvector, cross-tool memory, everything stays on your machine.

Turn LinkedIn saved posts into a queryable knowledge base you can search, chat with, and connect to Claude or ChatGPT through MCP.

Managed persistent-memory API for AI agents over MCP; memory that scores importance, links concepts, and learns from outcomes.

Local-first memory across sessions where Markdown files stay the source of truth and the search index is a rebuildable artifact.

Manage TTRPG campaign databases, wiki, and knowledge graphs

Hosted MCP for project intelligence, source-backed context, reviewed memory, and code graph tools.

Local-first shared memory and task coordination for AI coding agents. One Go binary, MCP server, markdown files you own. Hooks for Claude Code and Codex CLI (and their desktop apps).

Governed, self-hosted memory for AI agents — writes queue for human approval; audit-backed recall over MCP.

Local-first, source-grounded memory for AI agents, with durable Markdown, citations, bitemporal history, and review-gated corrections over MCP.

One shared, versioned memory for your AI agents across Claude Code, Cursor, Kiro and Grok, with a source on every answer and full history.