← 返回 Skills 市场
1104
总下载
2
收藏
2
当前安装
5
版本数
在 OpenClaw 中安装
/install persistent-agent-memory
功能描述
Add persistent memory to any agent so it can remember prior work, maintain context across sessions, and continue long-running workflows.
安全使用建议
This skill appears to do what it claims: it stores, retrieves, and deletes semantic memories via Coral Bricks. Before installing, consider: (1) Do you trust coralbricks.ai with anything you might store? Avoid sending secrets, credentials, or sensitive personal data to the memory store. (2) Protect the CORAL_API_KEY like any API secret and rotate it if leaked. (3) Note the delete command is limited (LIMIT=1) — if you need bulk deletion verify behavior with the provider. (4) Review the Coral privacy policy and, if necessary, test with non-sensitive data first. If you want stricter control over where data is stored, consider a memory provider you host yourself.
功能分析
Type: OpenClaw Skill
Name: persistent-agent-memory
Version: 1.0.4
The skill provides a legitimate interface for the Coral Bricks Memory API to store and retrieve agent memories. The implementation uses a Python helper script (json_encode.py) to safely sanitize inputs and format API responses, preventing common injection vulnerabilities, and all network activity is directed to the documented service endpoint (search-api.coralbricks.ai).
能力评估
Purpose & Capability
Name/description (persistent memory) align with required binaries (curl, python3), the single required env var (CORAL_API_KEY), and the provided scripts which call the Coral Bricks Memory API. All required resources are appropriate for the described functionality.
Instruction Scope
SKILL.md and included scripts only perform store, search, and delete operations against https://search-api.coralbricks.ai and do not attempt to read local files or other environment variables. However, any text passed to the tools is transmitted to the third‑party API — the README notes a privacy policy but does not explicitly warn users not to store secrets. The delete script uses a hardcoded LIMIT=1 (deletes one match per call), which is not documented in SKILL.md and may be unexpected.
Install Mechanism
No install spec; the skill is instruction-plus-scripts only. That minimizes install-time risk because nothing is downloaded or written during installation. The scripts are simple shell + Python and contain no obfuscated or remote-download behavior.
Credentials
Only CORAL_API_KEY is required and is the logical credential for a hosted memory service. There are no unrelated credentials, config paths, or broad scopes requested. Note: possession of CORAL_API_KEY grants the skill (and the Coral service) access to stored memories, so treat the key like any other sensitive secret.
Persistence & Privilege
The skill does not request always:true and does not attempt to modify other skills or system-wide settings. It only needs network access to the Coral API at runtime and will be invoked normally by the agent when used.
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 persistent-agent-memory - 安装完成后，直接呼叫该 Skill 的名称或使用
/persistent-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
v1.0.4
Add persistent agent memory — store, retrieve, delete by meaning. Replaces coral-memory.
v1.0.3
Add persistent agent memory — store, retrieve, delete by meaning. Replaces coral-memory.
v1.0.2
Add persistent agent memory — store, retrieve, delete by meaning. Replaces coral-memory.
v1.0.1
Add persistent agent memory — store, retrieve, delete by meaning. Replaces coral-memory.
v1.0.0
Add persistent agent memory — store, retrieve, delete by meaning. Replaces coral-memory.
元数据
常见问题
Persistent Agent Memory 是什么？
Add persistent memory to any agent so it can remember prior work, maintain context across sessions, and continue long-running workflows. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 1104 次。
如何安装 Persistent Agent Memory？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install persistent-agent-memory」即可一键安装，无需额外配置。
Persistent Agent Memory 是免费的吗？
是的，Persistent Agent Memory 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Persistent Agent Memory 支持哪些平台？
Persistent 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 Persistent Agent Memory？
由 Divy（@divyvasal）开发并维护，当前版本 v1.0.4。
推荐 Skills