← Back to Skills Marketplace
OpenClaw Memory OS
by
Justin Liu
· GitHub ↗
· v0.1.21
· MIT-0
571
Downloads
0
Stars
0
Active Installs
22
Versions
Install in OpenClaw
/install openclaw-memory-os
Description
OpenClaw Memory-OS - Digital immortality service with conversation recording infrastructure (Phase 1) | 数字永生服务对话记录基础设施（第一阶段）
Usage Guidance
Do not install blindly. Because this skill only provides instructions to install an external npm package (which will execute third-party code and can scan your filesystem), audit the package before installing: use npm pack to inspect its contents, check package.json for postinstall scripts and the exact published version, review the repository at the verified commit referenced in the SKILL.md (confirm which commit is authoritative), and run the CLI in an isolated VM or container with network disabled first. Never enable AUTO-TRIGGER or run broad collection commands (e.g., collect --source ~/) until you confirm the installed version actually implements the path protections, confirmation prompts, and privacy filter it claims. If you lack the ability to fully audit, prefer not to install globally; instead run in a throwaway VM or avoid enabling autonomous agent invocation.
Capability Analysis
Type: OpenClaw Skill
Name: openclaw-memory-os
Version: 0.1.21
The openclaw-memory-os skill is designed for 'digital immortality' by recording conversations and collecting local files into a central repository (~/.memory-os/). It exhibits high-risk capabilities, including broad filesystem access via the 'collect' command and an 'auto_trigger' feature that automatically saves data based on keywords (skill.md, readme.md). While the documentation is exceptionally transparent about these risks, provides auditing steps, and claims a local-only architecture with zero runtime network calls, the inherent risk of automated data aggregation and the requirement for a global npm installation (npm install -g openclaw-memory-os) justify a suspicious classification.
Capability Assessment
Purpose & Capability
The stated purpose (local conversation-memory storage) reasonably requires a CLI/runtime (Node/npm) and local storage under ~/.memory-os. However the registry metadata above lists no required binaries while SKILL.md explicitly requires Node.js >=18 and npm and a global npm install; this mismatch is incoherent and should be clarified.
Instruction Scope
SKILL.md instructs installing an external npm package and running a CLI that can scan arbitrary filesystem paths and create ~/.memory-os/. That capability is consistent with the skill's goal but the documentation contains conflicting claims about privacy protections: SKILL.md claims confirmation prompts, privacy filter, and path protection in v0.3.0, while the included readme documents older behavior (v0.2.2) where auto-trigger saved immediately and the privacy filter was not integrated. If you install the package version that lacks these safeguards, the CLI could collect sensitive files. The skill also includes keywords for auto-triggering saves — enabling that autonomously would broaden its access to the user's conversation/content.
Install Mechanism
There is no embedded code in the skill bundle; SKILL.md directs a global npm install (npmjs.com). Installing an npm package globally is a common delivery method but executes third-party code and modifies system PATH (moderate risk). The install guidance even explicitly warns about code execution and recommends inspecting the package first, which is good practice.
Credentials
The skill does not request environment variables, credentials, or config paths beyond suggesting it will create and use ~/.memory-os/. No extraneous secrets are requested in the metadata. That is proportionate to a local-memory tool, but because the CLI can scan user directories, filesystem access is the primary sensitive capability.
Persistence & Privilege
always:false and no special platform privileges are requested. The only persistent effect is installing a global CLI binary and creating ~/.memory-os/. This is expected for a CLI tool, but combined with autonomous invocation (platform default) and the ability to enable AUTO-TRIGGER, it could lead to repeated/automatic collection if the installed package implements that feature without safeguards.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install openclaw-memory-os - After installation, invoke the skill by name or use
/openclaw-memory-os - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.21
No changes detected in this version; Skill metadata remains unchanged.
v0.1.20
**v0.3.0 is a major security and privacy upgrade.**
- Added confirmation prompts: always asks before saving any memory, including with AUTO-TRIGGER.
- Integrated privacy filter: automatically redacts sensitive data (e.g., API keys, passwords, emails).
- Enforced path protection: blocks collection from sensitive directories by default (e.g., ~/.ssh, ~/.aws, .env files).
- Safe Mode enabled: all security features are ON by default.
- Encryption framework added (data still plain JSON; full encryption coming in v0.3.1).
- AUTO-TRIGGER remains OFF by default for privacy.
v0.1.19
# openclaw-memory-os v0.1.19 Changelog
- No file changes detected in this release.
- Version and requirements remain aligned with v0.2.2 package.
- Security, privacy, and installation instructions unchanged.
- No functional, feature, or documentation updates introduced in this version.
v0.1.18
v0.1.18 Changelog
- No file or functionality changes in this release.
- Version alignment only; all features, documentation, and security configurations remain unchanged.
v0.1.17
Version 0.1.17 Changelog
- No file changes detected in this release.
- No new features, fixes, or documentation updates introduced.
v0.1.16
No file changes detected in this release.
- No functional, documentation, or configuration changes were made.
- Version remains consistent with prior release features and security.
v0.1.15
- Updated dependency verification to use a new commit hash for the underlying package.
- Now requires user confirmation before each save when AUTO-TRIGGER is enabled, providing double protection for privacy.
- Clarified documentation to reflect confirmation prompts, making security and privacy behaviors more explicit.
- No functional or code changes detected in this release.
v0.1.14
- AUTO-TRIGGER for keyword-based conversation recording is now OFF by default for improved privacy; users must explicitly enable it.
- Updated documentation and security notice to reflect opt-in design; manual commands are now the recommended/default interaction.
- Configuration fields updated: `default_enabled` renamed to `opt_in` and switched to false; instructions clarified for enabling/disabling auto-trigger.
- No new features or code changes—this update focuses on privacy defaults and related documentation.
v0.1.13
No changes detected in this release.
- Version bumped from 0.1.13 to 0.2.1 with no file or documentation changes.
- No updates or new features introduced.
- Behavior, features, and security model remain identical to the previous version.
v0.1.12
No file changes detected since the previous version.
- No updates or code changes in this release.
- Functionality remains identical to the previous version.
v0.1.11
openclaw-memory-os v0.2.1
- Updated minimum required package version to 0.2.1 and verified against a new commit.
- Version advanced from 0.2.0-phase1 to 0.2.1 in the skill metadata.
- No other user-facing changes or new features detected.
v0.1.10
No functional changes or new features in this version.
- No file changes detected compared to the previous release.
- All behavior remains identical to v0.2.0-phase1.
- No impact on privacy, usage, or installation.
v0.1.9
No user-facing changes were detected in this version.
- Internal update: verified package commit hash updated in SKILL.md.
- No file or feature changes; version number and documentation remain unchanged.
v0.1.8
No file changes detected for version 0.1.8.
- No updates or modifications were introduced in this version.
- Functionality and documentation remain identical to the prior release.
v0.1.7
# v0.1.7 Changelog
- AUTO-TRIGGER for conversation memory is now enabled by default: conversation data is automatically saved when trigger keywords ("记住", "remember", etc.) are detected.
- Saving occurs immediately and without confirmation; users are no longer prompted before data is recorded.
- Privacy and safety documentation updated with prominent warnings, opt-out instructions, and best practices for managing automatic saves.
- AUTO-TRIGGER feature is fully configurable via `~/.memory-os/config.json`; users can disable it for manual operation.
- Core infrastructure remains fully local with no network/on-device AI and 100% offline data retention.
v0.1.6
**Clarification: This version (v0.2.0 Phase 1) is infrastructure-only—no automatic conversation capture or auto-trigger for OpenClaw. All data collection is manual/API-driven.**
- Introduced core conversation recording infrastructure: storage, session management, and privacy modules.
- Guarantee of 100% local storage; no network calls, APIs, or real-time background monitoring.
- All memory/conversation recording requires explicit API usage; nothing is collected automatically.
- Added privacy filter module (8 default rules for sensitive info) and improved high-performance data access.
- CLI and auto-triggered conversation capture are not included, and planned for Phase 2.
v0.1.5
**v0.2.0 Phase 1 – Conversation Recording Foundation**
- Adds full conversation recording infrastructure, supporting session management and privacy filtering.
- Enables auto-triggered memory capture from conversational prompts (e.g., "remember..." or "记住...").
- Automatically extracts information such as names, dates, and events from conversations for structured storage.
- Performance improvements: <10ms write speed, <5ms cached reads, with high cache hit rate.
- 100% local storage and processing: still no external APIs, no network calls, and no API keys required.
- Comprehensive test coverage ensures production-readiness for conversation memory.
v0.1.4
openclaw-memory-os v0.1.4
- Added USAGE_EXAMPLES.md with usage examples and instructions.
- No changes to core logic or CLI; documentation improvement only.
v0.1.3
- Unified and simplified documentation by replacing multiple separate language files (SKILL-EN.md, SKILL-ZH.md, SKILL.md) with a single, consolidated skill.md supporting both English and Chinese.
- Added a new readme.md for general usage and project overview.
- Updated documentation to include additional links (ClawHub, npm, GitHub).
- Improved feature and CLI descriptions to clarify available and planned capabilities.
- Removed redundant or outdated documentation files for streamlined maintenance.
v0.1.2
v0.1.2 - Format Fix
修正 SKILL.md 格式以符合 ClawHub 标准。
Changes:
- 移除标题中的 emoji 表情符号
- 主标题: 🧠 Memory-OS Skill -> OpenClaw Memory-OS
- 所有 H2 section 标题改为纯文本
- 调整描述顺序，更符合标准格式
- 参考 ClawHub 官方 skill 格式规范
现在完全符合 ClawHub 标准格式。
Metadata
Frequently Asked Questions
What is OpenClaw Memory OS?
OpenClaw Memory-OS - Digital immortality service with conversation recording infrastructure (Phase 1) | 数字永生服务对话记录基础设施（第一阶段）. It is an AI Agent Skill for Claude Code / OpenClaw, with 571 downloads so far.
How do I install OpenClaw Memory OS?
Run "/install openclaw-memory-os" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is OpenClaw Memory OS free?
Yes, OpenClaw Memory OS is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does OpenClaw Memory OS support?
OpenClaw Memory OS is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created OpenClaw Memory OS?
It is built and maintained by Justin Liu (@zhenstaff); the current version is v0.1.21.
More Skills