← 返回 Skills 市场
lizhelong0907

Dist

作者 lizhelong0907 · GitHub ↗ · v3.0.0 · MIT-0
cross-platform ⚠ suspicious
393
总下载
0
收藏
2
当前安装
4
版本数
在 OpenClaw 中安装
/install memory-engine
功能描述
OpenClaw 3.8+ 智能上下文管理与记忆系统插件
安全使用建议
This plugin implements a local memory engine and mostly behaves as described, but check these before installing: - Packaging mismatches: the registry entry/metadata contains inconsistent names/paths and SKILL.md claims a bundled ONNX model (~90MB) that is not listed in the provided files. Ask the author or inspect the package to confirm the model file is actually included or whether the plugin will fall back to a simpler (less accurate) embedding method. - Persistent local storage: by default it creates/uses a SQLite DB at ~/.openclaw/memory/memories.db and will save extracted user/AI content and embeddings. If you don't want conversation content persisted, do not install or change dbPath to a controlled location or disable automatic saving via configuration. - Native dependencies: the package depends on better-sqlite3 and onnxruntime-node which install native binaries; review build steps, and install in an environment where you trust building native modules. - Configuration: you can limit exposure by setting a custom MEMORY_ENGINE_DB_PATH, disabling cleanup/autosave, or enabling debug to inspect behavior. If the missing model is a concern, request a release that includes the model or confirm the fallback behavior. Given the inconsistencies, I recommend obtaining a clear build/release artifact (or official npm package) and confirming presence of the model and manifest paths before trusting this plugin with sensitive conversations.
功能分析
Package: memory-engine (mcp) Version: 2.0.0 Description: Context management plugin using Context Engine API The memory-engine package is a context management plugin for the OpenClaw framework. Its primary function is to provide a local long-term memory system for AI agents. It uses better-sqlite3 for local data persistence and onnxruntime-node to run a local embedding model (all-MiniLM-L6-v2) for semantic search and knowledge extraction. The code includes logic for context compression, rule-based tagging, and similarity-based deduplication. No evidence of data exfiltration, remote code execution, or unauthorized file system access was found. The package operates entirely locally, storing data in the user's home directory under a dedicated plugin folder.
能力评估
Purpose & Capability
The code implements a local memory engine (SQLite store, embedding extraction, compression, rule engine) that matches the described functionality. However there are packaging/metadata mismatches: the top-level metadata shows the skill name as "Dist" while the plugin identifies itself as "memory-engine", and the SKILL.md claims an included ONNX model (~90MB) but the provided file list does not include a models/all-MiniLM-L6-v2.onnx file. These inconsistencies may be benign (packaging issues) but are unexpected.
Instruction Scope
SKILL.md and the runtime code focus on memory capture, semantic search, compression, and local storage. Runtime instructions and code operate on conversation messages and local DB files; they do not attempt to access unrelated system areas or remote endpoints. The code does read environment variables for configuration (DB path, model path, debug toggles) which is consistent with a configurable local plugin.
Install Mechanism
No install spec is included in the registry entry (instruction-only), but a full npm package layout and package.json with native dependencies (better-sqlite3, onnxruntime-node) are present. Installing via npm will pull native modules that may compile or install native binaries. That is expected for this plugin's functionality but increases installation complexity and risk compared to pure JS packages.
Credentials
The skill declares no required environment variables or credentials. The code does use several optional environment variables (HOME/USERPROFILE for default DB path, MEMORY_ENGINE_* flags for configuration, MEMORY_ENGINE_DEBUG, MEMORY_ENGINE_MODEL_PATH). These are proportional to its purpose (configuring DB path, model path, and debug). No credentials or unrelated service tokens are requested.
Persistence & Privilege
The plugin writes a SQLite DB to the user's filesystem by default (~/.openclaw/memory/memories.db) and stores conversation content and embeddings. This is expected for a memory plugin but is a sensitive capability — it persists potentially sensitive user data locally. The plugin is not marked always:true and does not request other skills' config, but users should be aware it will store conversations on disk.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install memory-engine
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /memory-engine 触发
  4. 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
v3.0.0
No changes detected for version 3.0.0. - No file changes or new features introduced. - Documentation and functionality remain the same as version 2.0.0.
v2.0.2
- Major refactor: switched from src/ and dist/ TypeScript sources to direct JavaScript with type definitions. - Added: New JavaScript and .d.ts files for all major modules (compressor, embedding, extractor, memory-engine, rule-engine, store, types). - Removed: TypeScript source files and compiled distribution files. - Documentation files (CONFIG.md, MODEL_DOWNLOAD.md, README.md) were removed. No updates to SKILL.md content.
v2.0.1
- Bumped version to 2.0.1. - Updated package.json and package-lock.json dependencies. - No changes to user-facing features or documentation.
v2.0.0
Memory Engine 2.0.0 - 全新发布,支持 OpenClaw 3.8+ 的智能上下文管理和记忆系统插件 - 增加本地向量存储,基于 SQLite + ONNX,无需连接外网 - 支持语义搜索和相似度去重,提升记忆质量 - 自动知识提取与记忆类型分类(fact/experience/lesson/preference/skill) - 全新「重要性评分」功能,自动过滤低价值记忆 - 提供编程接口与 OpenClaw 插件工具集 - 内置 MiniLM-L6-v2 ONNX 模型,无需单独下载
元数据
Slug memory-engine
版本 3.0.0
许可证 MIT-0
累计安装 2
当前安装数 2
历史版本数 4
常见问题

Dist 是什么?

OpenClaw 3.8+ 智能上下文管理与记忆系统插件. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 393 次。

如何安装 Dist?

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

Dist 是免费的吗?

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

Dist 支持哪些平台?

Dist 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 Dist?

由 lizhelong0907(@lizhelong0907)开发并维护,当前版本 v3.0.0。

💬 留言讨论