Best Persistent AI Skills & MCP Servers
70 curated Persistent skills and MCP servers — install any of them into Claude, Cursor, ChatGPT, n8n, or any AI stack with one command.
Codex Memory
Local persistent memory for Codex agents that captures, searches, and reuses project knowledge.
Grok Faf
Persistent Project Context for xAI Grok. IANA-registered .faf format, MCP server on a URL, Vercel-deployed.
Server
MCP server providing persistent memory capabilities for AI assistants like Claude
Faf
Persistent Project Context for Cursor, IDEs and VS Code. IANA-registered .faf format, 25 MCP tools, 309 tests.
Sigil
Persistent memory for AI coding agents. Local-first knowledge engine with atomic facts, entity graph, and hybrid retrieval. Auto-integrated with Claude Code via hooks; MCP-native for Cursor, Continue, Cline, Windsurf, and any other MCP client.
Local Memory
Local Memory MCP Server - AI-powered persistent memory system for Claude Code, Claude Desktop, Gemini, Codex, OpenCode and other MCP-compatible tools
Claudex
Persistent memory + FTS5 search for Claude Code conversations. MCP server exposes your ~/.claude/projects/ history as queryable memory for any MCP-compatible AI agent.
In Memoria
Persistent intelligence infrastructure for agentic development
Ori Memory
Cognitive architecture for persistent AI agent memory. Knowledge graph with learning retrieval, ACT-R decay, and spreading activation. Markdown-native, local-first, zero cloud. MCP server + CLI.
Iranti
Memory infrastructure for multi-agent AI systems
Chat Relay
Powerful Cross-IDE Context Sharing via MCP. Persistently sync AI memories and chat sessions between Cursor, VS Code, and more.
Specmem Hardwicksoftware
Your Claude Code sessions don't have to start from scratch anymore — SpecMem gives your AI real memory. It won't forget your conversations, your code, or your architecture decisions between sessions. That's the whole point. Semantic code indexing that act
Mindpm
Persistent project memory for LLMs via MCP. Never re-explain your project again.
Gitmem
Persistent learning memory for AI coding agents. Memory that compounds.
Zerodb Sequential Thinking
Persistent sequential thinking MCP — chain-of-thought reasoning that survives sessions, resumes across agents, and saves conclusions as plan artifacts. Powered by ZeroDB. Zero-config: agents self-provision a ZeroDB account on first run, no signup required
Memoir Cli
MCP server that gives Claude, Cursor, and Gemini long-term memory across sessions. Your AI remembers your codebase, decisions, and preferences — across tools and machines.
Claude Remind
MCP server for searching past Claude Code conversation history. Local BM25 search over JSONL logs with persistent index, secret redaction, solved-hint, and instant claude --resume.
Ainative Zerodb Memory
AINative ZeroDB Memory MCP Server - 18 tools for agent memory: 9 memory + 5 write-back (Slack, Gmail, Calendar, GitHub, Notion) + 4 plan artifacts (persistent plans/PRDs across sessions with diff history). Auto-context middleware. Production-ready for Cla
Engram
Engram — Persistent Memory Cortex for AI coding agents. Gives agents session continuity, change tracking, decision logging, and project intelligence across sessions.
Cortex
Persistent memory for AI coding assistants. Injects context from past sessions into every LLM request.
Repomemory
Your codebase never forgets. Persistent, structured memory for AI coding agents.
Mac Pilot
Sandbox-protected macOS automation MCP server with a persistent recipe DB, Electron CDP fallback, and self-correcting per-app knowledge
Browser Link
MCP server that bridges Claude Code, OpenCode, GitHub Copilot CLI and other MCP clients to a Chrome tab. Per-tool permissions, multi-agent mode (multiple MCP clients sharing one bridge), persistent UI map across sessions.
Kairos
MCP server for agent automation: persistent memory and deterministic workflow execution for AI agents and chats
About Persistent skills on iClaude
iClaude is the universal install layer for AI skills. Every Persistent skill on this page can be installed into Claude Code, Claude Desktop, Cursor, ChatGPT, n8n, Codex, and more — using a single copy-paste command. No config drift, no per-stack adapters, no manual MCP wiring.