← 返回 Skills 市场
34145
总下载
34
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install agent-memory
功能描述
Persistent memory for AI agents to store facts, learn from actions, recall information, and track entities across sessions.
安全使用建议
Install only if you want an agent to keep local cross-session memory. Do not store API keys, passwords, financial details, regulated data, or confidential business information unless you have an explicit policy for doing so. Periodically inspect, export, or delete the database, and use a separate custom database path for different users or projects.
功能分析
Type: OpenClaw Skill
Name: agent-memory
Version: 1.0.0
The OpenClaw AgentMemory skill bundle is a self-contained, SQLite-based persistent memory system for AI agents. All code and documentation are aligned with its stated purpose of storing facts, lessons, and entities. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, obfuscation, or prompt injection attempts against the analyzing agent. The skill uses standard Python libraries, manages its database in a user-specific directory (`~/.agent-memory/memory.db`), and explicitly states 'No external dependencies' in `requirements.txt`, indicating a low supply chain risk.
能力评估
Purpose & Capability
The capability matches the stated purpose: persistent facts, lessons, entity tracking, recall, export, and deletion/cleanup. Stored content may include personal preferences or relationship context, so users should manage what is saved.
Instruction Scope
The skill suggests adding a session-start/session-end memory protocol to agent instructions. That can influence future sessions through saved memories, but it is disclosed and directly tied to the memory function.
Install Mechanism
Artifacts show normal installation guidance, no install hook, no external dependencies, and no obfuscated setup behavior. requirements.txt states it uses the Python standard library.
Credentials
The default storage path is documented as ~/.agent-memory/memory.db, with custom-path and in-memory options. The code uses local SQLite only and does not show network transmission, credential harvesting, or broad local file indexing.
Persistence & Privilege
Persistence is the central feature and is implemented as a local database created under the user's home directory by default. There is no evidence of background daemons, privilege escalation, or hidden persistence beyond the documented database.
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 agent-memory - 安装完成后，直接呼叫该 Skill 的名称或使用
/agent-memory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
v1.0.0
Initial release - SQLite-backed persistent memory for AI agents
元数据
常见问题
Agent Memory 是什么？
Persistent memory for AI agents to store facts, learn from actions, recall information, and track entities across sessions. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 34145 次。
如何安装 Agent Memory？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install agent-memory」即可一键安装，无需额外配置。
Agent Memory 是免费的吗？
是的，Agent Memory 完全免费（开源免费），可自由下载、安装和使用。
Agent Memory 支持哪些平台？
Agent Memory 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 Agent Memory？
由 Dennis（@dennis-da-menace）开发并维护，当前版本 v1.0.0。
推荐 Skills