XMemo MCP server

XMemo CLI

One private memory layer for every AI agent.

Install, authenticate, diagnose, and connect XMemo across editors, CLIs, and autonomous agents from one production-ready command line.

English · 简体中文

Quick start · Integrations · Connection modes · Commands · Security

@xmemo/client is the official control plane for connecting AI tools to XMemo. It makes setup repeatable, keeps credentials out of project files, and gives every supported client a consistent path to durable, user-owned memory.

The package is deliberately small: the CLI runtime, safe client configuration, behavior profiles, XMemo skills, and marketplace metadata. Server code, databases, deployment files, logs, and internal operations remain outside the npm distribution.

Architecture

Why XMemo CLI

and smoke checks share one predictable interface.

• One control plane — login, diagnostics, configuration, profiles, updates,

credential; it never embeds the credential value.

• Private by design — generated project configuration references a

integrations instead of duplicating the same capability through MCP.

• Native where it matters — OpenClaw and Hermes use dedicated memory

cover modern editors, terminals, and agent runtimes.

• Portable everywhere else — hosted Streamable HTTP MCP and local stdio

dry-run, or explicit confirmation before making changes.

• Safe automation — supported setup and removal paths offer preview,

file allowlist and release provenance.

• Small supply-chain surface — the npm package is governed by an explicit

Quick start

npm install -g @xmemo/client
xmemo login
xmemo doctor
xmemo setup codex
xmemo status

Replace codex with your client. Preview a configuration before writing it:

xmemo setup cursor --dry-run

Shortened. The full README is on GitHub.