Hierarchical long-term memory architecture for AI assistants with MCP support

Reference implementation for the Part II architecture paper (Zenodo 10.5281/zenodo.20374393) — dual-index FAISS memory, 42-opcode quaternionic VM, 5-phase retrieval, 36 tools, MCP server for Claude clients.

Contextual Memory Intelligence for AI Systems - Persistent memory, cognitive tools, and adaptive reasoning capabilities for LLMs Experimental memory system for LLMs (see MemMimic for optimized version)

The highest-scoring AI memory system ever benchmarked that isn't reliant on LLM reranking. And it's free & burns less tokens.

Hermes Memory System — 让 Claude Code 拥有真正的长期记忆 (8 phases, 117 tests, 12 MCP tools)

Model Context Protocol (MCP) server with temporal knowledge graph memory system for AI agents

A transparent, Markdown-backed, L0-L3 tiered hybrid memory system for AI agents with CBT safety and enterprise multi-tenancy support. Powered by MCP. 中文：为 AI Agent 打造的透明 Markdown 白盒与 L0-L3 分层混合记忆系统，兼顾 CBT 心理安全与企业级多租户支持，由 MCP 驱动。

Persistent local MCP/CLI memory system for AI agents. CPU-only, 98.94–99.15% R@5 on LongMemEval. Named after Mnemosyne (Greek: μνήμη, memory).

A-MEM Agentic Memory System - MCP Server for IDE Integration (Cursor, VSCode) | Dual-Storage: ChromaDB + NetworkX DiGraph with explicit typed edges | Based on Zettelkasten

Agent memory: SQLite fact store + Git wiki + keyword bridge. Multi-agent memory system for AI agents. No embeddings, no vector DB. Zero-dependency Python CLI with MCP server.

CeeSafe: a memory-safe systems language with modern syntax, compiled to portable C. Its compiler, ceesafec, is written in CeeSafe.

Structured memory system for AI assistants. Eliminates context loss with branch notes, tacit knowledge, and project context. Local MCP integration for Cursor IDE.

Give your AI agent full native Windows control via System Informer MCP — inspect processes, services, network, memory & more in C.

A Model Context Protocol (MCP) server implementation designed for AI agents to monitor and interact with Linux servers (Ubuntu, CentOS, RedHat, etc.). This server provides comprehensive system information including CPU, memory, disk, network, and process data through both MCP protocol and HTTP REST API

A Model Context Protocol (MCP) server implementation designed for AI agents to monitor and interact with Linux servers (Ubuntu, CentOS, RedHat, etc.). This server provides comprehensive system information including CPU, memory, disk, network, and process data through both MCP protocol and HTTP REST API

A system health and cleanup MCP server for **Odysseus**. It checks disk, memory, processes and battery, finds large files, and can clean up old temp files.

Give your AI agent full control of Windows. A native C MCP (Model Context Protocol) server built on System Informer / Process Hacker — 54 tools for processes, threads, memory, handles, services, network & more.

A Model Context Protocol (MCP) JS server implementation designed for AI agents to monitor and interact with Linux servers (Ubuntu, CentOS, RedHat, etc.). This server provides comprehensive system information including CPU, memory, disk, network, and process data through both MCP protocol and HTTP REST API

Engram - file-system-based memory management system for AI agents that grows with you & your teams, across agents, projects, and devices.

This is a personal knowledge base system established based on Karpathy's wiki concept. "Enable all AI tools to permanently access your local personal memory system."

A memory system for Cline that tracks progress between conversations.

MCP server for system memory monitoring and process management

Emotional Memory Management System for AI Agents

An MCP search and memory system for Joplin Notes

cmk — the CLI for core-memory-kit. Per-project, in-repo memory system for Claude Code.

An agent memory system with a causal core — facts, temporal state, and decision→outcome causal edges on one SQLite store

MCP server exposing live system metrics to Claude -CPU, memory, disk, processes, and network info

☀️Helios MCP: Give your AI permanent memory & personality! Install once, AI remembers forever. No more repeating context through versioned memory, behavioral & pattern learning, and multi-agent sync. UV-powered FastMCP server to teach your AI preferences and working styles that evolve through usage. Not a RAG system! Try today!☀️

Human-like neural memory system - Neuron-based persistent memory with Hebbian learning for AI agents

Local MCP memory system for AI agents with durable filesystem storage, Redis-backed short-term context, and a keyboard-first Qt/QML GUI.

Robot Memory - Persistent memory system for robotic AI agents

Comprehensive memory management system for LLM agents implementing episodic, semantic. Built in Rust with MCP server support for Kiro CLI

Persistent memory system for AI agents — SQLite + FTS5, MCP server, agent isolation, Obsidian sync. Zero dependencies.

Local-first persistent memory system for AI agents with hybrid search, graph reasoning, and MCP integration

A cognitive memory system for model continuity

AI agent memory system powered by Modern Hopfield Networks — no LLM calls, no database, one matrix multiply

Memory infrastructure for multi-agent AI systems

Claude Code Memory - Standardized project memory system for Claude Code

Long-term memory system for AI assistants — persistent, searchable, self-organizing memory powered by semantic search, knowledge graphs, and reinforcement learning

Living memory system for AI assistants — SQLite + MCP with decay, learning, and knowledge graph

AI Memory Management MCP System for LLMs - 让LLM善用思考，善用记忆

The memory layer for AI · Adaptive Memory And Fact Ordering System · Remote MCP server

Zero-Token-Waste Memory Engine, Knowledge Graph & Notes System for AI Coding Agents via MCP.

A persistent memory system for Cursor IDE — Hooks + MCP hybrid, auto-recall at session start, dual-layer global/project memory, bilingual full-text search.

Zettelkasten-based agent memory system with bidirectional links

ZettelForge: Agentic Memory System with vector search, knowledge graph, and synthesis

Full-featured long-term memory system for Claude Code via MCP — hybrid retrieval, smart extraction, auto-capture, intelligent forgetting

Native TypeScript AI memory system and MCP server (Zero-LLM, LanceDB)

Omnex is not a search tool. It is the memory substrate for the agentic era — the data layer that sits beneath AI agents, AI operating systems, and human-AI interaction. What exists today (file systems, folder hierarchies, manual search) is legacy. Omnex is the foundation of what comes next.

Multi-tenant memory system MCP server with vector search and relationships

Memory System for Cursor using MCP - Provides persistent context awareness for Claude

Native TypeScript AI memory system and MCP server (Zero-LLM, LanceDB)

Local Memory MCP Server - AI-powered persistent memory system for Claude Code, Claude Desktop, Gemini, Codex, OpenCode and other MCP-compatible tools

Robot Memory - Persistent memory system for AI robots. MCP Server + hybrid search + spatial retrieval.

Portable session-memory system for agents: provenance-carrying session evidence and queryable read models, with Codex as the current production adapter.

Local-first unified memory system for AI agents — downloads the signature-verified auxly binary.

A powerful, production-ready context management system for Large Language Models (LLMs). Built with ChromaDB and modern embedding technologies, it provides persistent, project-specific memory capabilities that enhance your AI's understanding and response quality.

A memory system using mem0 for AI applications. Enables long-term memory for AI agents as a drop-in MCP server.

Pluggable, multi-store memory for any AI system — episodic, semantic, temporal-graph and dialectic user memory in one library.

Persistent shared memory and coordination MCP server for multi-agent AI workflows. The memory component of the Junto system. MongoDB + ChromaDB. Production-tested with 6+ agents over 500+ sessions.