XMemo

XMemo: Memory OS for AI Agents

[XMemo logo]

[CI] [npm version] [Skill version] [Node.js version] [MIT license] [MCP compatible] [MCP Badge] [Glama quality score]

XMemo is a user-owned Memory OS for AI agents: persistent memory, project context and session continuity with agent identity, provenance and governed access, shared across AI clients through MCP, the CLI and a public REST API surface.

English · 简体中文 | Documentation · Hosted MCP

Quick start · What this repo contains · Beyond MCP · Integrations · Connection modes · Plugins · Commands · Versioning · Security

What this repository contains

• @xmemo/client: the official xmemo CLI for setup, diagnostics, behavior profiles, and memory commands.
• MCP distribution: hosted Streamable HTTP configuration (https://xmemo.dev/mcp) and the local xmemo-mcp stdio server.
• XMemo Skill & native integrations: skills/xmemo for agent platforms and the native plugin index (src/plugins/index.json).
• Marketplace and registry metadata: canonical descriptors for MCP Registry (server.json), LobeHub (lhm.plugin.json), and AI agents (context7.json).

The hosted service implementation is private.

Beyond MCP

MCP is one access surface of XMemo, not the product boundary. XMemo provides a persistent, governed memory operating layer across AI tools and agents:

• Persistent Memory: store, search, list, and soft-delete durable facts, preferences, and operational knowledge across sessions.
• Context Recall: retrieve focused, relevant context on demand with token-budget controls and document expansions.
• Session Continuity & Working State: restart snapshots and state save/restore so agents resume context across process restarts.
• Project Context & Decisions: track project-scoped facts, TODOs, and durable decisions across agent workflows.
• Agent Identity & Provenance: track authorship and origin per memory record via agent instance attribution without conflating credentials.
• Governed Access: scoped tokens, OAuth where the client supports it, soft/hard deletion and sensitive-memory handling (governance details).
• Native Integrations & Skill: dedicated integration for OpenClaw, Hermes, XMemo Skill (ClawHub), and DeepSeek DSH (available, released and pilot-tested; integration maturity Preview).
• Access Surfaces: unified via Model Context Protocol, the local CLI (xmemo), and the public REST API.

Preview: Cloud Skills; Dream (off by default); Teams (Business plan not yet available). Knowledge Bases are available where enabled for the account.

XMemo CLI

@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

[XMemo CLI architecture]

Why XMemo CLI

• One control plane — login, diagnostics, configuration, profiles, updates, and smoke checks share one predictable interface.
• Private by design — generated project configuration references a credential; it never embeds the credential value.
• Native where it matters — OpenClaw and Hermes use dedicated memory integrations instead of duplicating the same capability through MCP.
• Portable everywhere else — hosted Streamable HTTP MCP and local stdio cover modern editors, terminals, and agent runtimes.
• Safe automation — supported setup and removal paths offer preview, dry-run, or explicit confirmation before making changes.
• Small supply-chain surface — the npm package is governed by an explicit file allowlist and release provenance.

Quick start

Guided onboarding (xmemo init)

For an interactive first-run experience across account authentication, detected clients, agent behavior instructions, MCP server setup, skills, and plugins, run:

npm install -g @xmemo/clientxmemo init

Flags and options:

• xmemo init --dry-run: View the full onboarding plan without performing network calls or disk writes.
• xmemo init --yes: Automatically accept and apply all onboarding steps without interactive prompts.
• xmemo init --json: Emit structured JSON for the plan or result envelope.
• xmemo init --client <id>...: Restrict onboarding to specific clients (e.g., cursor, codex, claude-code).
• xmemo start: Alias for xmemo init with quick-start walkthrough steps.

Global installation exposes xmemo as the primary command, and also provides client and memory-os as aliases.

Manual step-by-step setup

xmemo account loginxmemo doctorxmemo setup codexxmemo status

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

xmemo setup cursor --dry-run

Running with npx

You can also run any CLI command directly without a global install via npx @xmemo/client <command>:

# Check version or healthnpx @xmemo/client --versionnpx @xmemo/client doctor
# Guided onboarding without global installnpx @xmemo/client init
# Install skill or run MCP stdio servernpx @xmemo/client skill installnpx @xmemo/client mcp serve

[XMemo CLI setup workflow]

[!TIP] Start with xmemo init (or xmemo account login, xmemo doctor, and xmemo setup <client>). Hand-edit MCP configuration only when a client has no verified setup path.

How the commands fit together

The XMemo CLI architecture is built on four core design principles:

1. Unified Resource Grammar (xmemo <resource> <action>)

Every integration component is a first-class resource with predictable lifecycle actions:

• Composite commands: xmemo setup [<client>...], xmemo uninstall [<client>...], and xmemo status [<client>] orchestrate these resources in a single step according to the client's declarative profile.
• Backward-compatible aliases: Familiar commands such as xmemo mcp add (alias for mcp install), xmemo profile uninstall (alias for profile remove), and xmemo skill uninstall (alias for skill remove) remain fully functional and print a helpful one-line hint in interactive terminals.

2. Unified Target Resolver

When no client is explicitly passed, the CLI uses a deterministic three-tier precedence resolution model:

1. Explicit flag or argument: --client <id>, positional client argument, or --all.
2. Calling agent environment: Automatically identifies the calling agent runtime when running inside an agent session (e.g., CLAUDECODE / CLAUDE_CODE_ENTRYPOINT maps to claude-code, and CODEX_THREAD_ID / CODEX_SESSION_ID maps to codex).
3. Detected installed clients: Inspects local configuration paths and markers. If exactly one matching client is found, it is automatically selected; if multiple clients are found in interactive mode, an interactive picker is presented. The CLI never silently writes configuration to arbitrary unverified paths.

3. Plan, Confirm Once, Apply (PlanRunner)

Mutating commands follow a strict, atomic execution pattern:

1. Build Plan: Assemble an ordered sequence of actions across resources (e.g. plugin install followed by skill configuration).
2. Preview: Print the entire plan (including modified paths, commands, and unified diffs) to the terminal.
3. Confirm Once: Prompt [y/N] exactly once for the entire sequence. Re-running with --yes or -y bypasses the prompt; --dry-run displays the preview without mutation.
4. Apply Sequentially: Steps run in dependency order, stopping immediately upon first failure. Re-running an already configured client detects that all components are up to date and reports Nothing to do.

4. Declarative Client Registry

All client configurations, recipes, and capabilities are declared centrally in src/clients/registry.js. Command implementations are purely generic orchestrators with zero hardcoded client ID strings. Platforms can also be added dynamically at runtime via registerClient().

Supported integrations

The client registry also covers Devin Desktop (formerly Windsurf), Cline, Continue, Claude Desktop, Claude Code, Kimi Code, Muse Code, Zed, JetBrains, OpenCode, Qwen, Trae, and compatible MCP hosts. Run xmemo mcp list for the current machine-readable catalog.

For VS Code users looking for the dedicated editor extension, see the yonro/xmemo-vscode repository. For Cursor users looking for the dedicated plugin, see the yonro/xmemo-cursor-plugin repository. For Claude users looking for the dedicated plugin, see the yonro/xmemo-claude-plugin repository.

Connection modes

Hosted MCP

The recommended universal path is the XMemo Streamable HTTP endpoint:

https://xmemo.dev/mcp

OAuth-capable clients complete authentication in the browser. Other clients reference XMEMO_KEY without copying its value into repository files.

Generic configuration shape:

{  "mcpServers": {    "XMemo": {      "type": "streamable-http",      "url": "https://xmemo.dev/mcp",      "headers": {        "Authorization": "Bearer ${XMEMO_KEY}"      }    }  }}

Client configuration keys differ; prefer xmemo setup <client> over copying this generic example directly.

Local stdio MCP

xmemo-mcp is the dedicated stdio entry point for marketplaces and clients that launch a local process. Safe discovery exposes 20 tools, three prompts, and two documentation resources without a token. Tool execution still requires authentication.

After a global installation:

xmemo-mcp

Install-free MCP configuration:

{  "mcpServers": {    "XMemo": {      "command": "npx",      "args": [        "-y",        "--package",        "@xmemo/client@latest",        "xmemo-mcp"      ]    }  }}

xmemo mcp serve is equivalent when the CLI is already installed.

Native integrations

OpenClaw and Hermes have dedicated memory providers. Their default setup avoids installing a second, duplicate XMemo tool surface:

• OpenClaw: installs the pinned plugin clawhub:@xmemo/[email protected] without --force by default. Re-running setup gracefully detects existing installations; use --force to reinstall or overwrite.
• Hermes: installs the pinned provider package hermes-xmemo==1.1.3 via pip install without -U.
• Every install command prints the exact command before executing. Use --dry-run to preview actions without installing.

# Native OpenClaw plugin (clawhub:@xmemo/[email protected]) + XMemo Skillxmemo setup openclaw
# Native Hermes memory provider (hermes-xmemo==1.1.3)xmemo setup hermes

Add hosted MCP only when an explicit fallback is desired:

xmemo setup openclaw --with-mcpxmemo setup hermes --with-mcp

Use --mcp-only to skip the native integration and install only the hosted MCP fallback.

XMemo Skill install

The CLI installs the verified XMemo Skill locally into agent skill folders or a target directory:

• Installs into client skill directories:
  • Claude Code: ~/.claude/skills/xmemo-memory (global) or .claude/skills/xmemo-memory (project with --project)
  • Codex: ~/.codex/skills/xmemo-memory
  • OpenClaw: ~/.openclaw/skills/xmemo-memory
  • All other 21 clients remain null until officially documented.
• Defaults to the pinned @xmemo/[email protected] release from npm and verifies tarball integrity (sha512 SRI) before extraction.
• Override version with --version <semver> or explicitly opt into the latest release via --version latest.
• For air-gapped or offline installations, install from a local directory or packed tarball with --from <dir|tgz> (optional --integrity <sha512>).
• Manage client skills with skill status, skill update, and skill remove.
• Preview actions without writing files using --dry-run.
• Safety & Consent:
  • Interactive install prompts [y/N] before writing (Enter, EOF, or empty input cancels) unless --yes is specified.
  • Existing installs refuse overwrite without --force; when --force is used, a backup is created in ~/.xmemo/backups/skills/<client>/ (outside the agent skills directory).
  • skill remove only removes verified XMemo skill directories, refusing foreign folders, and reports the preserved backup location.

# Install to agent skill folder (Claude Code global, Codex, or OpenClaw)xmemo skill install --client claude-codexmemo skill install --client codexxmemo skill install --client openclaw
# Install OpenClaw skill globally (shared ~/.openclaw/skills)xmemo skill install --client openclaw --global
# Install to project-level skill folder (Claude Code project: .claude/skills/xmemo-memory)xmemo skill install --client claude-code --project
# Install for all detected supported clientsxmemo skill install --all
# Automatically resolve detected client(s) (or specify --client <id>)xmemo skill install
# Install into a custom directory pathxmemo skill install --dir ./custom-skill-dir
# Non-interactive install (skips [y/N] prompt)xmemo skill install --client codex --yes
# Replace existing installation (creates backup in ~/.xmemo/backups/skills/<client>/)xmemo skill install --client codex --force --yes
# Update alias (equivalent to skill install --force)xmemo skill update --client codex --yes
# Inspect installation status across clientsxmemo skill statusxmemo skill status --client codexxmemo skill status --all --json
# Remove installed skill from an agent folder (refuses non-XMemo folders)xmemo skill remove --client codex --yesxmemo skill remove --client claude-code --project --yes
# Dry run previewxmemo skill install --client codex --dry-run

Standalone curl & PowerShell installers

For environments without Node.js or @xmemo/client, XMemo provides standalone HTTPS installers at https://xmemo.dev/skill/install (POSIX sh) and https://xmemo.dev/skill/install.ps1 (PowerShell).

The installer is agent-aware and automatically resolves the correct target directory for your active agent:

# Claude Code: installs to ~/.claude/skills/xmemo-memorycurl -fsSL https://xmemo.dev/skill/install | XMEMO_SKILL_AGENT=claude-code sh
# Codex: installs to ${CODEX_HOME:-$HOME/.codex}/skills/xmemo-memorycurl -fsSL https://xmemo.dev/skill/install | XMEMO_SKILL_AGENT=codex sh
# OpenClaw: install via OpenClaw CLIopenclaw skills install @xmemo/xmemo --version 1.1.48
# Windows (PowerShell):# $env:XMEMO_SKILL_AGENT="claude-code"; irm https://xmemo.dev/skill/install.ps1 | iex# $env:XMEMO_SKILL_AGENT="codex"; irm https://xmemo.dev/skill/install.ps1 | iex

[!TIP] Prompt for your AI Agent (copy and paste directly into Claude Code, Codex, or another agent):

text

Install the standalone XMemo Skill into your skills directory: run the installer from https://xmemo.dev/skill/install (on Windows, https://xmemo.dev/skill/install.ps1) with XMEMO_SKILL_DIR set to your skills directory plus /xmemo-memory. Run the doctor command it prints to verify the installation, then reload your skills and follow the Skill's first-run steps. Follow your normal safety checks and do not use elevated privileges.

Target resolution precedence (first match wins):

1. XMEMO_SKILL_DIR: Installs to the specified directory.
2. XMEMO_SKILL_AGENT=claude-code|codex: Installs to the explicit agent's skills directory (openclaw redirects to openclaw skills install xmemo).
3. Auto-detection: Automatically detects Claude Code (CLAUDECODE=1) or Codex (CODEX_THREAD_ID, CODEX_SESSION_ID, or CODEX_HOME).
4. Home directory discovery: If only ~/.claude or only ~/.codex exists in HOME, selects that agent.
5. Fallback: Installs to ./xmemo-skill with a warning on stderr explaining that AI agents will not automatically load the skill from this directory.

Safety & Replacement:

• Refuses to overwrite existing installations unless XMEMO_SKILL_FORCE=1 is provided.
• When replacing, moves the previous installation to ~/.xmemo/backups/skills/<agent>/<name>-<timestamp> (safely outside agent skill search paths).
• After installation, prints the absolute install path, the verification doctor command (node <path>/scripts/xmemo-skill.mjs doctor --anonymous), and a prompt to reload your agent.

Agent plugins

The CLI provides a curated, static index of verified agent plugins shipped directly in @xmemo/client. Each entry contains a pinned version, release tag, and exact Git commit SHA resolved at release time.

ℹ️ Strict Separation Rule: xmemo plugin installs agent plugins only (e.g. @xmemo/openclaw-memory). Skills are installed exclusively via xmemo skill install (e.g. @xmemo/xmemo).

Commands:

# List available plugins (excluding legacy entries)xmemo plugin list
# Include legacy pluginsxmemo plugin list --all
# View plugin details and verification metadataxmemo plugin info <id>
# Preview install plan without executingxmemo plugin install <id> --dry-run
# Install with explicit confirmation (prompts [y/N] by default)xmemo plugin install <id>
# Non-interactive installxmemo plugin install <id> --yes
# Specify profile for deepseek-dshxmemo plugin install deepseek-dsh --profile default --yes
# Specify custom target directory for git-dir pluginsxmemo plugin install claude-code --yes --dir ~/.custom-plugins/claude-code
# Open plugin documentation or marketplace in browserxmemo plugin install <id> --open
# Check installation statusxmemo plugin status [<id>]

Security & Consent:

• Only verified plugin IDs from the static index are accepted; arbitrary URLs and unknown IDs are rejected with exit code 2.
• Interactive install always displays the execution plan and requires explicit consent ([y/N], defaulting to Cancel on empty input or EOF).
• --dry-run guarantees zero disk writes and zero spawned processes.
• Marketplace and manual plugins display exact step-by-step instructions from the plugin repository during plugin install <id> (pass --open to open docs in browser).
• Git directory plugins (claude-code) clone into a stable per-user location (~/.xmemo/plugins/<id>), support --dir <path> override, verify the checked-out HEAD commit byte-for-byte, and output the exact load command (claude --plugin-dir <dir>). On commit mismatch, the directory is immediately removed.
• Plugin child processes run in an isolated environment with authentication tokens (XMEMO_KEY, MEMORY_OS_MCP_TOKEN, XMEMO_TOKEN) scrubbed from argv and env.

Account and authentication

Account commands

Manage local authentication, stored credentials, and tokens through the account command family:

# Browser device loginxmemo account login
# Check active authentication statexmemo account status
# Optional remote verificationxmemo account status --verify
# Check or store token credentialsxmemo account token statusprintf '%s\n' 'your-token' | xmemo account token add --from-stdin --allow-plaintext
# Logout: remove locally stored XMemo credentials owned by the CLIxmemo account logout
# Non-interactive logoutxmemo account logout --yes

Safe account logout (xmemo account logout)

• Target removal: Removes only the user-scoped credential file owned by the CLI (~/.config/xmemo/credentials.json or OS config root).
• Explicit confirmation: Displays the target credential path and prompts Proceed with logout? [y/N] (defaulting to No) unless --yes is specified.
• Client & Agent Isolation: Preserves all client MCP configuration files (Cursor, Claude, VS Code, etc.) and agent-managed OAuth sessions.
• Privacy: Never displays or leaks token values in stdout, stderr, or JSON envelopes.
• Scripting: Requires --yes when --json is specified to prevent accidental headless logout.

Legacy authentication aliases

The legacy commands remain fully supported as backward-compatible aliases:

• xmemo login (alias for xmemo account login)
• xmemo auth status (alias for xmemo account status)
• xmemo auth-status (alias for xmemo account status)
• xmemo token <status|add|set> (alias for xmemo account token <status|add|set>)

In interactive human mode, legacy aliases emit a one-line deprecation hint to stderr. When run with --json or --help, the deprecation hint is suppressed.

Existing token import

Pipe an existing token through stdin so it does not appear in command history:

printf '%s\n' 'your-token' | xmemo account token add --from-stdin --allow-plaintextxmemo account token status --verify

PowerShell:

$xmemoToken = Read-Host "XMemo token"$xmemoToken | xmemo account token add --from-stdin --allow-plaintextRemove-Variable xmemoToken

For CI and managed workstations, expose XMEMO_KEY through the platform's secret manager. Do not commit it to .env, MCP configuration, logs, issue reports, or chat transcripts.

Universal --json output

Every command and subcommand supports --json for predictable scripting:

• On success: Outputs valid JSON on stdout with exit code 0.
• On error: Outputs a structured JSON error envelope { schemaVersion, ok: false, command, data: null, error: { code, message, ... } } on stdout with a non-zero exit code (e.g. exit code 2 for usage/input errors, 1 for internal/network errors).

Command reference

xmemo init [--client <id>...] [--yes] [--dry-run] [--json]
# Backward-compatible aliasxmemo start [--json]

# High-level client configurationxmemo setup <client> [--url <url>] [--no-profile] [--json] [--force]xmemo setup <client> --dry-runxmemo setup --all [--write] [--profile] [--force]
# Direct MCP server configurationxmemo mcp servexmemo mcp listxmemo mcp config --client <client-id> [--base-url <url>] [--json]xmemo mcp add <client-id> [--write] [--config <path>]xmemo mcp proxy [--port 8765] [--base-url <url>]
# Workspace behavior profilesxmemo profile install <client-id> [--target <path>] [--dry-run]xmemo profile show <client-id> [--target <path>] [--json]xmemo profile status <client-id> [--target <path>] [--json]xmemo profile uninstall <client-id> [--target <path>] [--yes]

# Install verified pinned skill into agent skill foldersxmemo skill install [--client <id>|--all] [--project] [--dir <path>] [--dry-run] [--yes] [--force] [--json]
# Inspect installation status across clientsxmemo skill status [--client <id>|--all] [--json]
# Remove installed skill from an agent folder (refuses non-XMemo folders)xmemo skill remove --client <id> [--project] [--yes] [--json]
# Update skill installation (creates backup in ~/.xmemo/backups/skills/<client>/)xmemo skill update [--client <id>|--all] [--yes] [--json]

xmemo plugin list [--all] [--json]xmemo plugin info <id> [--json]xmemo plugin install <id> [--dry-run] [--yes] [--open] [--dir <path>] [--json]xmemo plugin status [<id>] [--all] [--json]

xmemo memory add --content "Remember this" --path notes/example --jsonxmemo memory search "example" --jsonxmemo memory read <id> --jsonxmemo memory list [--path-prefix <prefix>] [--project <name>] [--query <text>] [--type <type>] [--all] [--limit <n>] [--offset <n>] --jsonxmemo memory delete <id> [--reason <text>] [--yes] --jsonxmemo memory restore <id> [--yes] --jsonxmemo memory import --file memories.jsonl [--dry-run] [--idempotency-key <key>] [--yes] --jsonxmemo memory ledger-delete --id <transaction-uuid> --yes --jsonxmemo context recall "resume this task" --include-knowledge --jsonxmemo state save --current-task "ship the client" --next-action "run tests" --jsonxmemo state restore --jsonxmemo restart snapshot --jsonxmemo restart restore --snapshot-id <snapshot-id> --json
xmemo knowledge add --base <base-id> --file ./guide.pdf --title "Guide" --jsonxmemo knowledge search "setup" --base <base-id> --jsonxmemo knowledge read <item-id> --json > knowledge-view.jsonxmemo knowledge update <item-id> --text "Updated" --from knowledge-view.json --publish --yes --json
xmemo dream preview --wait --jsonxmemo dream show <run-id> --json > dream-view.jsonxmemo dream apply <run-id> --item <candidate-id> --from dream-view.json --yes --json
xmemo cloud-skill list --jsonxmemo cloud-skill add --file ./SKILL.md --jsonxmemo cloud-skill show <skill-id> --json > skill-view.jsonxmemo cloud-skill update <skill-id> --from skill-view.json --file ./SKILL.md --jsonxmemo cloud-skill run <skill-id> --input ./args.json --from skill-view.json --yes --json

xmemo login --scopes memory:read,memory:write,memory:restore,knowledge:read,knowledge:write

xmemo account login [--base-url <url>] [--allow-plaintext] [--json]xmemo account logout [--yes] [--json]xmemo account status [--verify] [--base-url <url>] [--json]xmemo account token status [--verify] [--json]xmemo account token add --from-stdin --allow-plaintext [--json]xmemo account token set --from-stdin [--allow-plaintext] [--json]
# Backward-compatible aliases (emit one-line deprecation note on stderr in human mode)xmemo loginxmemo auth statusxmemo auth-statusxmemo token statusxmemo token add --from-stdin --allow-plaintext

# Diagnostics and environment validationxmemo doctor [--services [memory,dream,knowledge,cloud-skill]] [--base-url <url>] [--json]xmemo doctor --discovery [--base-url <url>] [--json]xmemo doctor --client <client-id> [--config <path>] [--smoke] [--auth oauth|key] [--fix] [--json]
# Probes, updates, and environmentxmemo status [--url <url>] [--json]xmemo update [--dry-run] [--json]xmemo env [--example] [--shell bash|powershell|cmd] [--json]xmemo privacy [--json]xmemo --version [--json]
# Safe removal (only XMemo-owned entries and profiles are removed)xmemo uninstall <client> --dry-runxmemo uninstall <client> --yesxmemo uninstall --all --dry-runxmemo uninstall --all --yes --profiles
# Backward-compatible aliases (emit one-line deprecation note on stderr in human mode)xmemo smoke --client codexxmemo discovery show

Run xmemo help or xmemo <command> --help for complete, version-matched options.

Client notes

xmemo setup codexxmemo doctor --client codex --smoke
xmemo setup cursor

xmemo setup geminixmemo setup antigravity

xmemo loginxmemo setup openclawopenclaw xmemo status

xmemo loginxmemo setup hermes

xmemo loginxmemo setup copilotxmemo mcp proxy

Security by default

Credential precedence and compatibility aliases are documented by:

xmemo env example --shell bashxmemo privacy

For private or self-hosted deployments, set XMEMO_URL or pass --url <service-url>. MEMORY_OS_URL remains a compatibility alias.

Package boundary

Published to npm:

bin/docs/assets/src/README.mdLICENSE

Not published:

.github/docs/analysis/docs/architecture/docs/design/test/coverage/server codedatabase migrationsdeployment fileslogs and local state

Development

npm installnpm run release:checknpm run lintnpm testnpm run pack:dry-run

Before proposing a release, run the complete package gate:

npm run prepublishOnly

The local stdio server can be inspected directly:

node bin/mcp-stdio.js

Versioning

This repository distributes two independent products with decoupled version tracks:

• CLI (@xmemo/client): Published to npm.
  • Version source: package.json.
  • Tag convention: cli-v* (legacy tags through version 0.4.181 used v0.4.xxx).
  • View versions on npm (@xmemo/client).
• Skill (xmemo): Published to ClawHub and distributed via xmemo.dev.
  • Version source: skills/xmemo/scripts/xmemo-skill.mjs (SKILL_VERSION).
  • Tag convention: skill-v*.
  • View versions on ClawHub (xmemo). GitHub Releases for skill releases explicitly carry the Latest release badge to support automated installer and server fallback downloads.

Release model

Normal releases are produced by GitHub Actions from the exact tagged commit, not from a mutable branch checkout or a developer workstation:

develop → CLI version sync → test → cli-v tag → GitHub Actions → npm publish --provenance

The CLI package and hosted MCP service intentionally have separate version streams:

• CLI/npm version: package.json, package-lock.json, and the npm package entry in server.json.
• Hosted MCP/Registry version: the top-level server.json.version and lhm.plugin.json. This version follows the deployed XMemo service.

node scripts/check-release-version.mjs verifies both contracts. A cli-vX.Y.Z tag must equal the CLI/npm version and publishes only npm. The MCP Registry is published separately with the Publish MCP Registry metadata workflow using mcp-vX.Y.Z, which must equal the hosted MCP/Registry version. The separate npm publish workflow is manual recovery only, so creating a GitHub Release cannot publish twice. CLI npm publishing uses OIDC trusted publishing (environment: npm, id-token: write); static NPM_TOKEN is no longer used. Manual recovery via .github/workflows/publish.yml requires its own trusted publisher entry on npmjs.com.

Documentation and support

Canonical service documentation lives at docs.xmemo.dev. This repository documents the client; the pages below document the hosted service it connects to.

• XMemo
• MCP server reference
• Adding a new client
• Issues
• Releases

License

MIT © 2025–2026 Yonro