← Back to Skills Marketplace
OpenViking
by
Zayn Jarvis
· GitHub ↗
· v1.0.3
5794
Downloads
10
Stars
44
Active Installs
5
Versions
Install in OpenClaw
/install openviking-skill
Description
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".
Usage Guidance
Review before installing. Use it only for documents you intentionally want indexed, avoid broad private directories and secrets, protect ov.conf API keys, keep the MCP server bound to localhost, and verify the upstream repository before running setup.
Capability Analysis
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.
Capability Assessment
Purpose & Capability
The stated RAG and semantic-search purpose matches the documented MCP server, query/search tools, and add_resource ingestion capability.
Instruction Scope
The skill allows adding files, directories, and URLs to vector memory but does not set safe path limits, require confirmation before ingestion, or explain exclusions for sensitive data.
Install Mechanism
Setup is disclosed and user-directed: it clones the upstream OpenViking repository, runs uv sync, creates ov.conf, and prompts the user to add API keys; no hidden install behavior was found.
Credentials
Volcengine/Ark API keys are clearly required for embeddings and LLM answers, and the MCP server is documented as localhost-bound, but users should understand indexed content and queries may be processed by those provider services.
Persistence & Privilege
Persistent vector database storage is documented as data/, but the skill does not provide retention, deletion, cleanup, or recovery guidance for content added to the knowledge base.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install openviking-skill - After installation, invoke the skill by name or use
/openviking-skill - Provide required inputs per the skill's parameter spec and get structured output
Version History
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
Metadata
Frequently Asked Questions
What is OpenViking?
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". It is an AI Agent Skill for Claude Code / OpenClaw, with 5794 downloads so far.
How do I install OpenViking?
Run "/install openviking-skill" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is OpenViking free?
Yes, OpenViking is completely free (open-source). You can download, install and use it at no cost.
Which platforms does OpenViking support?
OpenViking is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created OpenViking?
It is built and maintained by Zayn Jarvis (@zaynjarvis); the current version is v1.0.3.
More Skills