← 返回 Skills 市场
396
总下载
1
收藏
2
当前安装
7
版本数
在 OpenClaw 中安装
/install memory-indexer
功能描述
短期记忆关键词索引工具 - 自动提取关键词、建立索引、搜索记忆，支持关联发现、时间线视图、重要记忆标记、三级级联搜索、会话备份与精简等功能。版本 2.0.0
安全使用建议
Before installing: 1) Inspect install.sh and update.sh — they will copy hooks and modify AGENTS.md/MEMORY.md/HEARTBEAT.md to make the skill run automatically; if you don't want that, do not run install.sh and perform manual installation. 2) The repository includes backup files (index.json and many session .md) containing session metadata and 'Session Key' strings — treat these as sensitive; remove or review them before placing the skill in your workspace. 3) Review embedding.py if you plan to enable semantic search: it can use local models or external providers (which may require API keys and network access). 4) If you decide to proceed, install it in a sandbox or non-production environment first, and avoid running automated auto-config steps; prefer manual symlink and running commands selectively. 5) If you need help auditing specific scripts (install.sh, session_backup.py, embedding.py), consider sharing them for a targeted review.
功能分析
Type: OpenClaw Skill
Name: memory-indexer
Version: 2.0.1
The memory-indexer skill bundle is a comprehensive tool for managing long-term memory in OpenClaw agents through keyword indexing, vector semantic search, and session compaction. The code is well-structured and includes proactive security measures, such as regex-based filtering in `memory-indexer.py` to prevent sensitive technical IDs and API tokens (e.g., GitHub, OpenAI, AWS) from being indexed. File operations and system integrations (like modifying AGENTS.md or adding crontab entries) are transparently documented and strictly aligned with the stated purpose of memory persistence and workspace optimization. No indicators of data exfiltration, malicious execution, or unauthorized persistence were found.
能力评估
Purpose & Capability
The code and instructions match a memory-indexer (python, jieba, embedding support). However the repository contains multiple backup files (index.json, sync-state.json, many session .md files) that include session metadata and 'Session Key' strings — shipping real session backups inside the skill is unexpected and exposes sensitive data unrelated to packaging the tool itself. The install scripts also auto-configure AGENTS.md/MEMORY.md/HEARTBEAT.md to prioritize this skill, which is functionally coherent but intrusive.
Instruction Scope
SKILL.md and README instruct running install.sh which will install dependencies, create symlinks into ~/.openclaw, copy hooks to ~/.openclaw/hooks/, and modify OpenClaw config to make the skill run early/on heartbeat. Those steps go beyond local CLI tooling: they change system/agent configuration and enable automatic behaviors. The included backup files in the repo mean installing will place pre-populated data (potentially sensitive) on disk.
Install Mechanism
No registry install spec was published, but SKILL.md metadata suggests pip-installing jieba and the repo provides install.sh/update.sh. The recommended install clones the GitHub repo and runs install.sh — a normal pattern. However the repo contains large backup files that will be written into the skills directory when installed, increasing privacy risk. No shorteners or unknown download hosts were observed.
Credentials
The declared requirements are minimal (python3, jieba) and requires.env lists none. The README and code support optional embedding providers (HuggingFace, Ollama, MiniMax) and env vars (EMBEDDING_PROVIDER, HF_MODEL_NAME) but these are optional. The main concern is not requested credentials but the presence of stored session keys and conversation backups included in the repository, which are sensitive data that do not need to be bundled with a generic installer.
Persistence & Privilege
The skill is not marked always:true, but install.sh and README explicitly modify OpenClaw configuration (AGENTS.md, MEMORY.md, HEARTBEAT.md) and install Hooks that cause automatic behavior (prioritizing this indexer, heartbeat tasks). That gives the skill persistent and autonomous effects across agent runs. This matches the stated goal (automatic search/backup) but is a higher-privilege/intrusive integration and should be opt-in and reviewed before enabling.
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 memory-indexer - 安装完成后，直接呼叫该 Skill 的名称或使用
/memory-indexer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
v2.0.1
更新至 v2.0.1：新增三级级联搜索、向量语义搜索、会话备份与精简、Hook 支持等
v1.0.0
首次发布
v2.0.0
Major update: Skill changed from "memory-indexer" to a new "ai-ppt-generator" with Baidu AI integration.
- Completely replaced the original memory indexing tool with an AI-driven PPT generator.
- Added smart template selection based on topic content (business, technology, education, etc).
- Introduced user-interactive workflow for choosing template style or auto-select option.
- Included scripts for listing templates, auto-categorization, and PPT generation with Baidu API.
- Updated usage instructions and detailed step-by-step agent flow.
- Old memory management scripts and files removed; now focuses solely on intelligent PPT generation.
v1.0.12
- Added backup files for index, stars, and sync-state with timestamped directories.
- Updated documentation: CHANGELOG.md, README.md, and README_EN.md with latest instructions and feature details.
- Improved installation (install.sh) and update (update.sh) scripts.
v1.0.11
Expanded functionality and documentation update:
- Enhanced description and feature list: now emphasizes advanced features like association discovery, timeline view, important memory marking, auto-sync, and cleanup.
- Updated installation and usage instructions with detailed, step-by-step commands.
- Added a comprehensive command table for all available operations.
- Clarified default index directories and configuration file locations.
- Removed optional Node.js hooks and related references.
- Updated homepage URL and refined integration guidance for OpenClaw and cron automation.
v1.0.10
- Updated project homepage and repository links to https://github.com/smallmj/memory-indexer
- Revised description and README content to clarify local-only memory indexing, searching, and snapshot backup features
- Added new section on security, with guidance about local file access and handling sensitive data
- Included recommendations for manual configuration instead of automated scripts
- Noted optional Node.js requirement for hook support
- Simplified feature list and installation instructions
v1.0.9
- 完善/丰富了功能文档，详细列出核心特性和使用命令
- 新增详细的安装、配置以及与 OpenClaw 集成说明
- 明确外部依赖及安装方法（Python 3.8+ 与 jieba 库）
- 提供脚本自动目录结构和数据文件说明
- 附加心跳同步与定时备份集成建议
元数据
常见问题
memory-indexer 是什么？
短期记忆关键词索引工具 - 自动提取关键词、建立索引、搜索记忆，支持关联发现、时间线视图、重要记忆标记、三级级联搜索、会话备份与精简等功能。版本 2.0.0. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 396 次。
如何安装 memory-indexer？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install memory-indexer」即可一键安装，无需额外配置。
memory-indexer 是免费的吗？
是的，memory-indexer 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
memory-indexer 支持哪些平台？
memory-indexer 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 memory-indexer？
由 smallmj（@smallmj）开发并维护，当前版本 v2.0.1。
推荐 Skills