viking-memory
OpenViking 长期记忆系统。用于语义检索用户偏好、历史对话、重要信息等。当需要召回用户之前提到的信息、查找相关上下文时使用此 Skill。
Why use this skill?
Enhance your OpenClaw AI agent with Viking Memory. Store user preferences, dialogue history, and custom knowledge for intelligent, persistent semantic retrieval.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/forvendettaw/viking-memoryWhat This Skill Does
Viking Memory is a robust, vector-based long-term memory system designed specifically for the OpenClaw AI agent ecosystem. It serves as the cognitive foundation for the OpenViking project, enabling the agent to transition from ephemeral, session-based interactions to a persistent, personalized experience. By utilizing advanced semantic retrieval techniques, Viking Memory allows your AI agent to store, index, and query personal preferences, past conversation histories, and critical domain knowledge. Unlike standard local storage, this skill transforms static information into a searchable knowledge base, ensuring that the context of previous interactions is never lost, even across long time intervals.
Installation
To integrate Viking Memory into your environment, use the OpenClaw package manager. Open your terminal and execute the following command:
clawhub install openclaw/skills/skills/forvendettaw/viking-memory
Ensure that the base service is running at http://127.0.0.1:18790 before attempting to perform operations, as the agent requires this local socket to persist and retrieve memory records.
Use Cases
- Contextual Recall: When a user asks "What was that book title I mentioned last week?", the agent can perform a semantic lookup to find the specific mention.
- Preference Management: Automatically store user habits, such as "I prefer my meeting summaries in bullet points," and retrieve them to optimize future outputs.
- Knowledge Persistence: Maintain state for ongoing projects, allowing the agent to pick up exactly where you left off, even after a restart.
Example Prompts
- "Look back through my memories and find the restaurant recommendations I saved last month."
- "I mentioned a new project idea earlier today, can you retrieve the details I stored?"
- "Save this note to my memory: My primary programming language for this project is TypeScript."
Tips & Limitations
- Precision vs. Recall: When searching, use specific keywords if you are looking for a exact fact, or natural language if you are looking for thematic context.
- Data Privacy: All data is stored locally. While this offers excellent privacy, ensure you back up your memory store if you hold critical information.
- Limitations: The search quality is dependent on the embedding quality. Avoid storing extremely sparse, short snippets that lack semantic context for better retrieval results.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-forvendettaw-viking-memory": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, file-read, file-write, external-api
Related Skills
memory-manager
三级记忆管理系统 (Three-Tier Memory Management)。用于管理 AI 代理的短期、中期、长期记忆。包括：(1) 滑动窗口式短期记忆，(2) 自动摘要生成中期记忆，(3) 向量检索长期记忆 (RAG)。当需要管理对话历史、优化上下文、构建个人知识库、或实现记忆持久化时使用此 Skill。
three-tier-memory
三级记忆管理系统 (Three-Tier Memory)。短期记忆滑动窗口 + 中期记忆自动摘要(LLM) + 长期记忆向量检索(RAG)。当需要管理对话历史、自动摘要、语义检索、构建个人知识库时使用此 Skill。
memory-manager
三级记忆管理系统 (Three-Tier Memory Management)。用于管理 AI 代理的短期、中期、长期记忆。包括：(1) 滑动窗口式短期记忆，(2) 自动摘要生成中期记忆，(3) 向量检索长期记忆 (RAG)。当需要管理对话历史、优化上下文、构建个人知识库、或实现记忆持久化时使用此 Skill。
openclaw-auto-doctor
实时监控 OpenClaw 日志，自动诊断错误，搜索解决方案，并自动修复问题或创建 Pull Request
memory-manager
三级记忆管理系统 (Three-Tier Memory Management)。用于管理 AI 代理的短期、中期、长期记忆。包括：(1) 滑动窗口式短期记忆，(2) 自动摘要生成中期记忆，(3) 向量检索长期记忆 (RAG)。当需要管理对话历史、优化上下文、构建个人知识库、或实现记忆持久化时使用此 Skill。