MemPalace Cloud

MemPalace Cloud gives your AI coding tools persistent memory across sessions. Pick your tool below and follow the guide — you'll be up and running in about two minutes.

Connect Claude Code to MemPalace Cloud — the AI memory tool that gives Claude Code persistent memory across sessions. Install the MemPalace skill in two commands.

Connect Codex CLI to MemPalace Cloud with the one-liner install script.

Connect Claude Desktop to MemPalace Cloud with MCP and memory instructions.

Connect Cursor to MemPalace Cloud with MCP settings and custom rules.

Connect ChatGPT to MemPalace Cloud via MCP Developer Mode.

Connect Claude.ai to MemPalace Cloud via custom MCP connectors.

Connect Cline (VS Code) to MemPalace Cloud over MCP with custom instructions.

Connect Zed to MemPalace Cloud via an MCP context server and agent rules.

Connect Windsurf (Cascade) to MemPalace Cloud over MCP with global rules.

What your AI tool can do with MemPalace Cloud.

Connect Sally.io to MemPalace Cloud and turn meeting summaries into structured memories — one main drawer per meeting plus separate drawers for decisions and tasks.

How to upgrade, manage subscription, and create a paid team.

- Your AI tool connects to your personal MCP server on every new session.
- Memories are stored, searched, and retrieved automatically during conversations.
- Facts, decisions, and context persist across sessions and across tools.
- New captures land in your Inbox — approve, edit, or reject before they become permanent.
- All data is EU-hosted and exportable at any time.

MCP (Model Context Protocol) server that exposes 70 tools spanning cognitive memory, working memory, sessions, agents, the L0–L3 knowledge hierarchy, orchestration tasks, and training pipelines. The server speaks stdio and is consumed by Claude Desktop, Claude Code, OpenCodex, and any MCP-aware client.

User-owned memory for AI agents over remote MCP. Save, search, recall, update, and manage scoped memories across Copilot, Claude, ChatGPT, IDEs, and CLIs.

A persistent memory server for Large Language Models, designed to integrate with the Claude desktop application. It supports tiered memory, semantic search, and automatic memory management.

A server that provides a memory system for LLMs, enabling persistent conversations with various providers like OpenAI, Anthropic, and OpenRouter.

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

Local Work Model for AI agents that learns from real outcomes.

Auditable, self-improving knowledge & memory for AI agents over MCP — citation-enforced answers and a replayable why-trace, self-hosted on Postgres.

One shared, versioned memory for your AI agents across Claude Code, Cursor, Kiro and Grok, with a source on every answer and full history.

Operational memory for AI agents that persists across sessions and tools.

Self-hosted MCP server giving AI agents persistent memory — Markdown source of truth, hybrid BM25+embedding search, typed graph relations.