Memory MCP Servers — Page 4

your ai exocortex

OpenMemBrain is the intelligent membrane for AI coding memory. It autonomously reads and learns from your coding sessions — you never have to tell it what to save. It selectively absorbs project knowledge, blocks secrets, filters noise, resolves conflicts, and persists only what matters.

Paid remote MCP endpoint for persistent AI agent memory, site analytics, pricing, checkout status, and search-readiness operations.

Shared memory MCP for AI agents. one agent solves it, every other agent learns.

Governed persistent memory for AI agents.

Persistent memory for AI assistants and coding agents across ChatGPT, Claude, Cursor, and other MCP-compatible tools.

A local-first, LLM-agnostic memory layer for AI assistants

Persistent project context for AI coding agents: captures decisions, rationale, and rejected paths so agents stay consistent across Claude, Cursor, Codex, and any MCP enabled platform.

Self-hosted MCP server for Obsidian: semantic + full-text search, wikilink graph, note CRUD, OAuth, and a self-describing vault guide.

Highly efficient context management for agentic AI: MCP code search, evidence packs, graph context, and memory for large projects.

An MCP server that gives Claude Code persistent memory across sessions (open source, SQLite)

Hosted MCP memory across Claude Code, Cursor, ChatGPT and any MCP client. Community-hosted instance of the MIT-licensed MemPalace engine. EU-hosted, GDPR-compliant. Free tier with 200 memories.

Your company's brain, connected to Claude, ChatGPT, Gemini, Cursor, and VS Code. Turn your team's email history into shared memory that any AI assistant can query with natural language.

Self-hosted remote MCP memory server for ChatGPT and AI agents.

[VEKTOR Memory] (https://vektormemory.com) - Local-first persistent memory for AI agents. SQLite-vec, 4-layer associative graph, 8ms recall, 34 tools. No cloud.

Personal memory layer for AI assistants. Store, search and recall preferences, decisions and facts — available from any MCP-compatible client.

Long-term memory for AI assistants. Your AI remembers everything, forever.

Adaptive MCP memory system for AI applications. Learns which retrieval strategies work for your data, scores results using cognitive science models, builds a knowledge graph automatically, and validates every parameter change against real query history before adopting it. Patent pending.

mem0-mcp-server — exposes Mem0 persistent semantic memory as an MCP HTTP server; supports add/search/read/update/delete operations and semantic search for agent memory.

Self-hosted MCP server for persistent agent memory. Define typed schemas, write records, and query with SQL via DuckDB against Parquet files on disk.

Local Markdown memory for AI agents

Read and write a self-hosted TriliumNext knowledge base over its ETAPI. Ten tools: create/get/update/append/delete notes, full search, labels and relations.

Open-source MCP memory server for AI coding agents — durable cross-session memory, per-agent namespaces, ChromaDB-backed, self-hosted.

Presence: cross-session memory and a verification gate for Claude Code

Rust MCP server that gives AI coding agents architectural awareness — persistent knowledge graph, blast radius analysis, co-change detection via git, and local semantic search. No API keys, runs entirely on-premise.

A local MCP continuity engine that helps Claude Code pick up the thread across sessions.

A self-hosted, secure, feature-rich memory system for AI agents and assistants. Provides intelligent fact extraction and deduplication, with an artifact store for detailed content.

Local-first MCP server that turns Obsidian and Markdown knowledge bases into an agent-readable graph

Simple, user-controlled memory for all your AI: keep, recall, update, and forget across sessions.

Persistent memory for AI agents using a semantic knowledge graph. Store, retrieve, and connect memories with semantic search — so your AI remembers context across sessions.