← 返回 Skills 市场

Meshmorize

Name: Meshmorize
Author: mozz0

作者 mozz0 · GitHub ↗ · v3.1.0 · MIT-0

cross-platform ✓ 安全检测通过

总下载

当前安装

版本数

在 OpenClaw 中安装

/install meshmorize

功能描述

🧠 Multi-layer memory system: fresh layer, mesh graph, auto-log, cross-layer search, compliance check

使用说明 (SKILL.md)

MeshMorize 🧠

Multi-layer memory system for LLM agents. Fresh daily layer, mesh graph indexing, auto-logging, cross-layer search, and full compliance checks.

Built for OpenClaw. Works with any agent that can run Python.

Layers

Layer	File	Purpose
Fresh	`memory/fresh/today.md`	Daily notes, 5-day rotation
Mesh	`memory/mesh.json`	Graph nodes + search index
Log	`scripts/auto_log`	Auto-log every interaction
Search	`scripts/memory_search`	Cross-layer search (fresh → daily → mesh → raw → long-term)
Check	`scripts/memory_check`	10-point compliance check (`memcheck`)

Quick start

mem-bridge init          # Rotate fresh layer, create today.md
auto_log "msg" "reply"   # Log an interaction
memory_search "query"    # Search all memory layers
memcheck                 # Full 10-point compliance check

Tools

Tool	Source
`mem-bridge`	`memory/bridge.py` — fresh-layer rotation + checkpoint management
`auto_log`	`scripts/auto_log.py` — interaction logger
`memory_search`	`scripts/memory_search.py` — multi-layer search across all memory stores
`memcheck`	`scripts/memory_check.py` — 10-point compliance check runner

Install

Put bridge.py in memory/ and scripts in scripts/ of your agent workspace. Symlink or add to PATH:

ln -s $(pwd)/scripts/* ~/.local/bin/
ln -s $(pwd)/memory/bridge.py ~/.local/bin/mem-bridge

On session start, run:

mem-bridge init

Source

https://github.com/mozz0/MeshMorize

Made by mozz0 · Released under MIT

安全使用建议

Install only if you want an agent memory system that can retain interaction logs across sessions. Review what the missing companion scripts do before running them, avoid logging secrets or regulated data, and remove the ~/.local/bin symlinks and workspace memory files if you later uninstall it.

能力标签

crypto

能力评估

✓ Purpose & Capability

The skill is explicitly about multi-layer agent memory, auto-logging, fresh-layer rotation, graph indexing, and search; these capabilities are coherent with the advertised purpose.

ℹ Instruction Scope

The instructions tell the agent to log interactions and run initialization at session start, which is broad but plainly stated and tied to the memory workflow.

ℹ Install Mechanism

Install steps create symlinks in ~/.local/bin and expect memory/scripts directories in the agent workspace; this modifies the local filesystem but is visible and limited to making the tools runnable.

✓ Credentials

The artifact is a single SKILL.md with no bundled executable scripts, no credential collection, no network automation, and no hidden install behavior.

ℹ Persistence & Privilege

Persistent storage is central to the skill, with files such as memory/fresh/today.md and memory/mesh.json documented, though users should understand that logged prompts and replies may persist beyond a session.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install meshmorize
安装完成后，直接呼叫该 Skill 的名称或使用 /meshmorize 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v3.1.0

Major update: MeshMorize 3.1.0 introduces a new multi-layer memory system, replacing the previous self-improvement logging workflow. - Fully rewrote documentation and workflow in SKILL.md for the "MeshMorize" system. - Added support for a daily "fresh" memory layer, mesh graph indexing, auto-logging, and cross-layer search. - Introduced 10-point compliance checks and streamlined tool usage (mem-bridge, auto_log, memory_search, memcheck). - Removed legacy docs, templates, hooks, scripts, and references related to self-improvement logging and OpenClaw integration. - Simplified installation and setup instructions for agent-agnostic deployment.

v1.0.0

MeshMorize 1.0.0 – Initial release - Introduces a multi-layer memory system with daily (fresh), mesh graph, and auto-log layers. - Supports cross-layer memory search (from fresh to long-term storage). - Includes a 10-point compliance check for memory operations. - Provides command-line tools for initialization, logging, searching, and compliance checks. - Compatible with OpenClaw and any Python-based agent architecture.

元数据

Slug meshmorize

版本 3.1.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 2

常见问题

Meshmorize 是什么？

🧠 Multi-layer memory system: fresh layer, mesh graph, auto-log, cross-layer search, compliance check. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 40 次。

如何安装 Meshmorize？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install meshmorize」即可一键安装，无需额外配置。

Meshmorize 是免费的吗？

是的，Meshmorize 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

Meshmorize 支持哪些平台？

Meshmorize 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 Meshmorize？

由 mozz0（@mozz0）开发并维护，当前版本 v3.1.0。