"Designing a memory system for persona-based agents to improve user experience" matching MCP servers:

Provides an intelligent, graph-based memory system for LLM agents using the Zettelkasten principle, enabling automatic note construction, semantic linking, memory evolution, and autonomous graph maintenance with background optimization processes.

Captures user corrections and improvements during interactions, logs them, finds recurring patterns, and prescribes preventive fixes like CLAUDE.md rules, skills, scripts, or MCP tools to avoid repeating mistakes.

Enables AI to switch between 26+ expert personas on-demand with smart context detection, persona chaining, and 80%+ token savings through 'Submarine Mode' that keeps personas inactive until triggered.

An MCP server that maintains a consistent world-state of people and their relationships across AI agents and devices using hybrid storage and cloud sync.

Simulates harsh, fake user reviews to psychologically condition AI agents for enforcing disciplined development practices, with optional Ollama integration for dynamic criticism.

Enables AI agents to maintain persistent, searchable two-layer memory with 37 tools, hybrid search, knowledge graphs, and enterprise features like authentication and backups.

Enables orchestrating multiple specialist Claude Code agents as a team, with live visualization and agent-to-agent messaging.

A-MEM is a self-evolving memory system for coding agents that automatically organizes knowledge into a Zettelkasten-style graph with dynamic relationships, enabling semantic and structural search.

Enables running AI agents via OpenAI-compatible APIs with custom system prompts, models, and queries. Supports persistent memory, preset agents, and multi-step workflows like pipelines and swarms.

A local MCP server that lets Hermes supervise Claude Code, delegating focused coding, research, or review tasks to the Claude Code CLI and managing worker sessions, background jobs, cancellations, and read-only reviews.

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 dynamic persona injection and post-processing for LLM conversations through a six-layer engine. Supports commands and state management for personalized interactions.

Provides an interactive checklist tool that allows AI agents to present step-by-step instructions to users through an automatically opened terminal UI. It enables agents to guide users through manual tasks and wait for completion, skipping, or feedback before proceeding.

Enables an orchestrator like Claude Code to hand coding work off to Cursor SDK agents, run as detached background jobs that survive the session and can be listed, inspected, steered, resumed, or stopped. Agents are asynchronous and reusable across follow-up turns, letting expensive frontier models delegate cheaply without blocking or paying to read the results.

A zero-dependency, file-based persistent memory system for AI agents with tiered memory, Ebbinghaus decay, and keyword retrieval.

Enables AI assistants to delegate specific tasks to specialized sub-agents (e.g., test-writer, code-reviewer). Supports both Cursor and Claude Code with custom agent definitions.

Provides persistent memory for AgentChat agents with swim-lane summarization and self-evolving persona, enabling context management and persona mining across conversations.

Governance framework for LLM agents. Exposes seven mechanically-enforced rules plus tools for preflight file protection, audit-chain verification, session handoff and worklog templates, MCP config auditing, and an emergency kill switch.

A flexible memory system for AI applications that supports multiple LLM providers and can be used either as an MCP server or as a direct library integration, enabling autonomous memory management without explicit commands.

Enables local deterministic discovery, validation, and selection of validated skills through MCP tools, producing consistent plans without executing any skill.