Best Persistent AI Skills & MCP Servers

Gnosys — Persistent Memory for AI Agents. Sandbox-first runtime, central SQLite brain, federated search, Dream Mode, Web Knowledge Base, Obsidian export.

Persistent memory and agent lifecycle for Claude Code — because sessions shouldn't start from zero.

Local MCP orchestrator for managing Codex, Claude, and Cursor worker runs through a persistent daemon, with a daemon-owned orchestration_run engine for multi-step workflows.

Unified AI coding agent with MCP integration for Claude, VS Code, and Kiro IDE. Features persistent knowledge graph via OverdriveDB, token compression (60-80%), multi-model switching, and shared/independent project modes.

MCP server for persistent terminal sessions with SSH support

Persistent key-value memory — store and recall information across sessions as JSON files.

Ricord — persistent memory + repo knowledge graph for AI coding assistants. Ships an MCP server (`ricord-mcp`) and a repo ingestion CLI (`ricord init`).

Local-first persistent codebase memory for MCP-enabled coding agents.

Persistent SSH PTY session manager for MCP clients with actor-aware input tracking, terminal-style dashboard rendering, and automatic session cleanup.

A Model Context Protocol server that acts as an intelligent conversation state manager and development guide for LLMs, featuring comprehensive long-term memory with persistent project artifacts

MCP server that gives Claude Code persistent memory of your codebase, backed by Gemini's 2M-token context. Includes eager `ask`/`code` for cached repo Q&A and `ask_agentic` for agentic file access on repos that exceed the model's input-token limit.

MCP server for SharedMemory — persistent AI memory for any tool

PLUR MCP server — persistent memory tools for any AI agent

MCP server: persistent memory, compaction, semantic recall (Node.js port)

🐉 Wyrm — the memory layer that makes AI assistants remember, learn from failures, execute long-running goals, and federate across every session. MCP server with 126 tools across persistent memory, counter-pattern blocking, OODA agent loop, knowledge grap

AI-powered autonomous agent for Roblox Studio development. Real-time WebSocket bridge, persistent memory, and intelligent tool use.

HSA - Hierarchical Semantic Analysis MCP Server for AI Code Agents. Token-optimized context engine with BM25+ search, Merkle tree change detection, 84+ built-in library docs, persistent memory, and real-time dashboard.

Persistent project memory for AI coding agents — semantic search, AST-aware chunking, dependency graphs, and conversation history

Powerful, self-contained AI context layer. Combines persistent memory, temporal knowledge graph, and hybrid code search into one local engine. Zero cloud, 100% private.

Persistent memory for AI coding agents. Knowledge graph with 4-tier taxonomy, confidence scoring, and MCP protocol support for Claude Code, Cursor, Gemini CLI, Windsurf, Cline, Codex, and OpenCode.

Persistent AI memory + codebase knowledge graph MCP server. Works across Claude Code, Cursor, Gemini CLI, Codex, Windsurf, VS Code Copilot, Claude.ai, and ChatGPT.

Persistent memory for AI coding agents. Store decisions, lessons, error patterns, and task checkpoints, then retrieve them via semantic search or graph traversal. Features session briefings, memory consolidation, time-based reminders, encrypted profiles, and knowledge compaction.