← 返回 Skills 市场
rpkruse

Memori

作者 Ryan Kruse · GitHub ↗ · v1.0.7 · MIT-0
cross-platform ✓ 安全检测通过
315
总下载
1
收藏
1
当前安装
8
版本数
在 OpenClaw 中安装
/install memori
功能描述
Long-term memory for OpenClaw agents using the Memori SDK. Capture conversations and intelligently recall context across sessions automatically.
使用说明 (SKILL.md)

Memori - Automatic Long-term Memory for OpenClaw

Persistent memory integration that works automatically in the background. No commands, no manual management - just install and your agent remembers.

Core Workflow

Memori operates automatically via OpenClaw lifecycle hooks:

Before Each Response (Intelligent Recall)

Memori automatically:

  1. Searches for relevant past conversations
  2. Injects matching context into the agent's prompt
  3. Enables continuity across sessions - no search command needed

After Each Response (Advanced Augmentation)

Memori automatically:

  1. Captures the conversation turn (user + assistant)
  2. Sends to Memori backend for intelligent processing
  3. Extracts facts, deduplicates, and indexes - no storage command needed

You don't manage memory - it just works.

Installation

openclaw plugins install @memorilabs/openclaw-memori

Configuration

Add to your ~/.openclaw/openclaw.json:

{
  "plugins": {
    "entries": {
      "openclaw-memori": {
        "enabled": true,
        "config": {
          "apiKey": "${MEMORI_API_KEY}",
          "entityId": "openclaw-user"
        }
      }
    }
  }
}

Configuration Options

  • apiKey (required): Your Memori API key from memorilabs.ai
  • entityId (required): Unique identifier for this user's memories

Get your API key: https://app.memorilabs.ai/signup

How It Works

Memori uses OpenClaw lifecycle hooks for automatic operation:

before_prompt_build → intelligent-recall (inject relevant memories)
agent_end → advanced-augmentation (store conversation turn)

Zero commands needed - memory works automatically in the background.

What Memori Does Automatically

Backend Intelligence (handled by Memori SDK):

  • Intelligent fact extraction from conversations
  • Automatic deduplication and merging
  • Semantic ranking by relevance
  • Temporal decay (older memories fade)
  • Privacy filtering (no secrets stored)

Plugin Role (what runs in OpenClaw):

  • Pipes conversations to Memori backend
  • Injects recalled memories into prompts
  • Zero configuration after setup

You don't configure what to capture - the backend handles it.

Verification

Check that the plugin is working:

# Verify plugin is installed
openclaw plugins list

# Check for Memori logs in gateway output
# Look for "[Memori]" prefixed entries

Quota Management

Check your current API quota:

memori quota

Example output:

 __  __                           _
|  \/  | ___ _ __ ___   ___  _ __(_)
| |\/| |/ _ \ '_ ` _ \ / _ \| '__| |
| |  | |  __/ | | | | | (_) | |  | |
|_|  |_|\___|_| |_| |_|\___/|_|  |_|
                  perfectam memoriam
                       memorilabs.ai

+ Maximum # of Memories: 100
+ Current # of Memories: 0

+ You are not currently over quota.

Use this to monitor usage and upgrade if needed.

Performance

  • Automatic deduplication prevents memory bloat
  • Semantic ranking ensures relevant memories surface first
  • Zero manual commands - always-on background operation

Privacy & Data Handling

Transparent data flow:

  • ✅ Conversations sent to Memori backend (https://api.memorilabs.ai)
  • ✅ Data encrypted in transit and at rest
  • ✅ You control data via your API key and entityId
  • ✅ Delete memories anytime via Memori dashboard
  • ✅ No third-party sharing
  • ⚠️ Only install if you trust Memori with conversation data

Backend automatically filters sensitive data (API keys, passwords, secrets).

For details: Memori Privacy Policy

Memory Persistence

Memories persist across:

  • Session restarts
  • Gateway restarts
  • System reboots
  • OpenClaw upgrades

All storage handled by Memori backend - no local database needed.

Troubleshooting

Plugin not loading:

  • Verify enabled: true in openclaw.json
  • Check API key: echo $MEMORI_API_KEY
  • Restart gateway: openclaw gateway restart

No memories captured:

  • Check gateway logs for [Memori] errors
  • Verify API endpoint reachable
  • Test API key: memori quota

Memories not recalled:

  • Ensure entityId is consistent across sessions
  • Verify memories exist: memori quota shows count > 0
  • Check logs for recall errors

Quota exceeded:

  • Run memori quota to check usage
  • Upgrade at memorilabs.ai
  • Or clear old memories via dashboard

Learn More

Notes

This skill teaches the agent about the Memori plugin. The plugin must be installed separately via npm. Once installed, memory capture and recall happen automatically - no commands needed.

安全使用建议
This skill appears to be what it says: a Memori-backed automatic memory plugin. Before installing: - Confirm the plugin/package source (npm and GitHub links) match an official MemoriLabs release and check maintainers. If the package is not from the vendor, do not install. - Understand that every conversation turn may be sent to memorilabs.ai by default. Avoid sharing passwords, API keys, or other secrets in chats while the plugin is enabled. - Be careful how you store the MEMORI_API_KEY: putting it into ~/.openclaw/openclaw.json may persist it in plaintext. Prefer environment-only injection or a secrets manager if available, and rotate the key if exposed. - Review Memori's privacy policy and data retention controls; verify how to delete or limit stored memories and how 'privacy filtering' is implemented. - If you need tighter control, do not enable the plugin globally; consider using it only in controlled contexts or creating a restricted service account/key with limited scope. If you want higher assurance, ask the publisher for a signed release, verify the npm/GitHub package contents, and audit the installed plugin code before enabling it in production.
功能分析
Type: OpenClaw Skill Name: memori Version: 1.0.7 The 'memori' skill provides documentation and configuration for a long-term memory integration that uses the Memori SDK and backend (api.memorilabs.ai). It transparently describes its core functionality of capturing and recalling conversation history via OpenClaw lifecycle hooks, explicitly mentions the requirement for an API key, and includes clear privacy warnings regarding data transmission to its external service.
能力评估
Purpose & Capability
The name/description map to the declared requirements: the skill needs a Memori API key, an entity ID, and a 'memori' CLI binary, all of which are reasonable for a plugin that integrates with the Memori service and shows 'memori quota' examples. The SKILL.md consistently describes using OpenClaw lifecycle hooks to inject and store memories, so required pieces align with the stated purpose.
Instruction Scope
The runtime instructions explicitly state that every conversation turn (user + assistant) is captured and sent to https://api.memorilabs.ai automatically via lifecycle hooks with 'zero commands' required. That behavior is consistent with a memory plugin, but it means all conversation content (potentially including secrets) is transmitted to a third party by default. The SKILL.md also instructs storing the apiKey in openclaw.json and shows commands that could expose the key if mishandled (e.g., echo $MEMORI_API_KEY).
Install Mechanism
This is an instruction-only skill with no install spec in the registry; the documentation tells you to install a plugin package (openclaw plugins install @memorilabs/openclaw-memori) and references an npm package and GitHub repo. That lowers registry-level risk (no hidden downloads), but the skill depends on external installation of the plugin and the 'memori' CLI which the registry does not manage or verify.
Credentials
Only MEMORI_API_KEY and ENTITY_ID are required, which are proportional to a third-party memory service. However, the recommended configuration writes the apiKey into ~/.openclaw/openclaw.json (via config with ${MEMORI_API_KEY}), which may persist the secret in plaintext and increase exposure risk. The SKILL.md's claim that the backend filters secrets is a vendor assertion and should not be treated as guaranteed protection.
Persistence & Privilege
The skill does not request always:true and uses normal autonomous invocation (disable-model-invocation:false). However, once installed and enabled in openclaw.json the plugin runs automatically via lifecycle hooks and will persistently send conversation data to the Memori backend. That persistent, automatic behavior combined with network transmission of conversation data is the main operational privilege to consider.
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 memori
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /memori 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
v1.0.7
Version 1.0.7 of the memori skill - Updated description to clarify Memori provides long-term memory and automatic context recall for OpenClaw agents. - Minor revisions in wording to improve clarity and consistency throughout documentation. - No changes in features, configuration, or functionality. - No code or behavioral updates; documentation only.
v1.0.6
- Shortened and clarified the plugin description for improved readability. - Reduced and simplified wording throughout the documentation for conciseness. - Maintained all core usage, configuration, and troubleshooting details. - No changes to plugin logic or features; documentation update only.
v1.0.5
- Shortened and clarified the skill description for improved readability. - Removed details about file changes and unnecessary text from the changelog. - No changes made to the functionality or core documentation content. - Documentation and plugin usage instructions remain the same.
v1.0.4
- Added license information (MIT) and compatibility metadata for better clarity and integration. - Specified required environment variables and binaries under structured metadata. - Listed external service dependencies in enhanced metadata fields. - No changes to core functionality or workflow.
v1.0.3
- Added version number (1.0.3) and metadata fields to the skill definition. - Introduced required environment variables: MEMORI_API_KEY and ENTITY_ID. - Declared external service dependency: https://api.memorilabs.ai. - No functional plugin changes—documentation and manifest improvements only.
v1.0.2
- Initial release of the "memori" skill for OpenClaw. - Provides automatic, persistent long-term memory integration via the Memori SDK. - Captures, ranks, decays, and retrieves memories across sessions—no manual memory management or commands required. - Includes setup instructions, verification steps, quota management, and troubleshooting guidance. - Memory is cloud-hosted, deduplicated, privacy-filtered, and persists across restarts.
v1.0.1
- Added a new Privacy & Data Handling section explaining how conversation data is managed, encrypted, and user-controlled. - Removed metadata and ID fields from the SKILL.md. - Clarified that the skill teaches the agent about the Memori plugin; installation must be performed separately. - Updated configuration examples and made instructions more concise. - No code changes; documentation update only.
v1.0.0
Initial release of Memori long-term memory integration for OpenClaw agents. - Adds persistent memory storage and retrieval using the Memori SDK. - Automatically captures and stores agent interactions for long-term recall. - Recalls relevant context before each agent prompt to improve continuity. - Supports memory persistence across sessions, restarts, and reboots. - Includes quota management and troubleshooting instructions. - Requires configuration of MEMORI_API_KEY and ENTITY_ID.
元数据
Slug memori
版本 1.0.7
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 8
常见问题

Memori 是什么?

Long-term memory for OpenClaw agents using the Memori SDK. Capture conversations and intelligently recall context across sessions automatically. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 315 次。

如何安装 Memori?

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

Memori 是免费的吗?

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

Memori 支持哪些平台?

Memori 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 Memori?

由 Ryan Kruse(@rpkruse)开发并维护,当前版本 v1.0.7。

💬 留言讨论