功能描述

RAG and semantic search via OpenViking Context Database MCP server. Query documents, search knowledge base, add files/URLs to vector memory. Use for document Q&A, knowledge management, AI agent memory, file search, semantic retrieval. Triggers on "openviking", "search documents", "semantic search", "knowledge base", "vector database", "RAG", "query pdf", "document query", "add resource".

使用说明 (SKILL.md)

OpenViking - Context Database for AI Agents

Name: OpenViking
Author: zaynjarvis

OpenViking is ByteDance's open-source Context Database designed for AI Agents — a next-generation RAG system that replaces flat vector storage with a filesystem paradigm for managing memories, resources, and skills.

Key Features:

Filesystem paradigm: Organize context like files with URIs (viking://resources/...)
Tiered context (L0/L1/L2): Abstract → Overview → Full content, loaded on demand
Directory recursive retrieval: Better accuracy than flat vector search
MCP server included: Full RAG pipeline via Model Context Protocol

Quick Check: Is It Set Up?

test -f ~/code/openviking/examples/mcp-query/ov.conf && echo "Ready" || echo "Needs setup"
curl -s http://localhost:2033/mcp && echo "Running" || echo "Not running"

If Not Set Up → Initialize

Run the init script (one-time):

bash ~/.openclaw/skills/openviking-mcp/scripts/init.sh

This will:

Clone OpenViking from https://github.com/volcengine/OpenViking
Install dependencies with uv sync
Create ov.conf template
Pause for you to add API keys (embedding.dense.api_key, vlm.api_key)

Required: Volcengine/Ark API Keys

Config Key	Purpose
`embedding.dense.api_key`	Semantic search embeddings
`vlm.api_key`	LLM for answer generation

Get keys from: https://console.volcengine.com/ark

Start the Server

cd ~/code/openviking/examples/mcp-query
uv run server.py

Options:

--port 2033 - Listen port
--host 127.0.0.1 - Bind address
--data ./data - Data directory

Server will be at: http://127.0.0.1:2033/mcp

Connect to Claude

claude mcp add --transport http openviking http://localhost:2033/mcp

Or add to ~/.mcp.json:

{
  "mcpServers": {
    "openviking": {
      "type": "http",
      "url": "http://localhost:2033/mcp"
    }
  }
}

Tools Available

Tool	Description
`query`	Full RAG pipeline — search + LLM answer
`search`	Semantic search only, returns docs
`add_resource`	Add files, directories, or URLs

Example Usage

Once connected via MCP:

"Query: What is OpenViking?"
"Search: machine learning papers"
"Add https://example.com/article to knowledge base"
"Add ~/documents/report.pdf"

Troubleshooting

Issue	Fix
Port in use	`uv run server.py --port 2034`
Auth errors	Check API keys in ov.conf
Server not found	Ensure it's running: `curl localhost:2033/mcp`

Files

ov.conf - Configuration (API keys, models)
data/ - Vector database storage
server.py - MCP server implementation

安全使用建议

Install only if you want an agent connected to a local OpenViking MCP knowledge base. Review or pin the cloned repository, use dedicated provider API keys, keep the server bound to localhost, and add only narrowly scoped documents you are comfortable storing in persistent vector memory.

功能分析

Type: OpenClaw Skill Name: openviking Version: 1.0.3 The OpenViking skill bundle is designed to set up and interact with a local RAG (Retrieval Augmented Generation) server. The `SKILL.md` provides clear, non-malicious instructions for the AI agent and user, without any evidence of prompt injection attempts to subvert the agent's purpose. The `scripts/init.sh` script performs standard setup tasks: cloning the OpenViking repository from `https://github.com/volcengine/OpenViking`, installing Python dependencies using `uv sync`, and creating a configuration template. There is no evidence of data exfiltration, persistence mechanisms, or other intentionally harmful behaviors. The instruction to install `uv` via `curl | sh` is a user-facing prerequisite, not an action directly executed by the skill itself, and `uv` is a legitimate tool.

能力评估

⚠ Purpose & Capability

The RAG and semantic-search purpose is coherent, but the advertised add_resource tool can add files, directories, and URLs into vector memory without documented path limits or exclusions.

⚠ Instruction Scope

The instructions are user-directed, but they do not define confirmation requirements, retention/deletion controls, path allowlists, or safety boundaries for adding local directories to the knowledge base.

ℹ Install Mechanism

The one-time setup script clones an external GitHub repository and runs uv sync. This is purpose-aligned, but the cloned source and dependency set are not pinned in the provided artifacts.

ℹ Credentials

Volcengine/Ark API keys and a local MCP server are expected for embeddings and LLM answers, but the registry metadata declares no credentials or capability tags, so users may not see those requirements upfront.

⚠ Persistence & Privilege

The skill creates a persistent vector database/data directory for agent memory, and the artifacts do not describe retention, isolation, or cleanup behavior.

版本历史

v1.0.3

RAG and semantic search via OpenViking Context Database MCP server

v0.1.0

OpenViking 0.1.0 – Initial Release - Adds RAG and semantic search capabilities via the OpenViking Context Database MCP server. - Supports querying documents, searching a knowledge base, and adding files/URLs to vector memory. - Introduces a filesystem-like organization for context management, supporting tiered context and directory-based retrieval. - Includes tools for full RAG pipeline, semantic search only, and resource addition. - Requires Volcengine/Ark API keys for operation.

v1.0.2

Changed default MCP server port from 8000 to 2033 to avoid common port conflicts

v1.0.1

Improved SEO and description. Added Context Database overview, tiered context explanation, and better trigger keywords for RAG, semantic search, knowledge base, and vector database queries.

v1.0.0

Initial publish of OpenViking MCP server for RAG and semantic search

元数据

Slug openviking

版本 1.0.3

许可证 —

累计安装 44

当前安装数 40

历史版本数 5

常见问题

OpenViking 是什么？

RAG and semantic search via OpenViking Context Database MCP server. Query documents, search knowledge base, add files/URLs to vector memory. Use for document Q&A, knowledge management, AI agent memory, file search, semantic retrieval. Triggers on "openviking", "search documents", "semantic search", "knowledge base", "vector database", "RAG", "query pdf", "document query", "add resource". 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 4941 次。

如何安装 OpenViking？

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

OpenViking 是免费的吗？

是的，OpenViking 完全免费（开源免费），可自由下载、安装和使用。

OpenViking 支持哪些平台？

OpenViking 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 OpenViking？

由 Zayn Jarvis（@zaynjarvis）开发并维护，当前版本 v1.0.3。

OpenViking