A tool for building a searchable knowledge base from documents and files. It can index content, search by meaning rather than exact words, browse resources, and provide summaries or full documents.

For importing files or folders, finding relevant passages with semantic search, exploring indexed resources, and reading summaries or complete sections.

It makes information spread across indexed files easier to find and review without manually opening each document.

openviking — Skill for Claude Code and Codex by swizardlv: A tool for building a searchable knowledge base from…

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods

npx agentmods add skills/swizardlv/openclaw_openviking_skill/openviking

Any agent

npx skills add swizardlv/openclaw_openviking_skill --skill openviking

Clone the repo

git clone --depth 1 https://github.com/swizardlv/openclaw_openviking_skill

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/swizardlv/openclaw_openviking_skill/openviking.svg)](https://agentmods.dev/skills/swizardlv/openclaw_openviking_skill/openviking)

Your own site

<a href="https://agentmods.dev/skills/swizardlv/openclaw_openviking_skill/openviking"><img src="https://agentmods.dev/badge/skills/swizardlv/openclaw_openviking_skill/openviking.svg" alt="Measured on agentmods" height="20"></a>

Per session 89 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 617 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00089	$0.00617
Opus 5	$0.00044	$0.00309
Sonnet 5	$0.00018	$0.00123
Haiku 4.5	$0.00009	$0.00062

Measured 6d ago against content hash 589ca26e344a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

openviking scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/viking.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

openviking/SKILL.md · 74 lines

How it starts

The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.

OpenViking Skill

Manage an OpenViking context database: index documents, semantic search, browse, and retrieve summaries.

Prerequisites

Python 3.9+ with openviking package installed (pip install openviking)
Config file at ~/.openviking/ov.conf with valid embedding and VLM credentials
Environment variable OPENVIKING_CONFIG_FILE=~/.openviking/ov.conf

If prerequisites are not met, guide the user through setup. See references/setup-guide.md.

Quick Reference

Index a file

python3 scripts/viking.py add /path/to/file.md

Index all files in a directory (recursive)

python3 scripts/viking.py add-dir /path/to/directory --pattern "*.md"

Semantic search

python3 scripts/viking.py search "query text" --limit 5

Browse resources

python3 scripts/viking.py ls [viking://resources/path]

Get summary

python3 scripts/viking.py abstract viking://resources/my_doc
python3 scripts/viking.py overview viking://resources/my_doc

Read full content

python3 scripts/viking.py read viking://resources/my_doc/section.md

Usage Notes

Data directory: Defaults to ./openviking_data in the current working directory. Override with --data-dir.
File name collisions: OpenViking uses file names (not full paths) as URIs. Avoid indexing files with identical names from different directories simultaneously.
VLM model: Use non-reasoning models (e.g. meta/llama-3.3-70b-instruct) for the VLM. Reasoning models return content in the wrong field.
Embedding model: nvidia/nv-embed-v1 (symmetric, 4096-dim) works without extra parameters. Asymmetric models (e.g. nv-embedqa-e5-v5) require input_type which OpenViking doesn't pass.

When to Use Python API vs CLI Script

CLI script (scripts/viking.py): For quick one-off operations from the shell.
Python API: For complex workflows, batch operations, or integration into other scripts. See references/python-api.md.

Read the full file on GitHub · 74 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

6d ago First seen · 74 lines · 89 tokens per session scan A 589ca26e344a

Subscribe to this mod's changes

openviking is a skill published in the GitHub repository swizardlv/openclaw_openviking_skill (23 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 89 tokens to every session and 617 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Data and AI Memory and context RAG and vectors

AgentDB Memory Patterns

Implement persistent memory patterns for AI agents using AgentDB. Includes session memory, long-term storage, pattern learning, and context management. Use when building stateful agents, chat systems, or intelligent assistants.

ruvnet/RuView · 45 tokens

pinecone-research

Agent RAG and long-term memory with Pinecone.

NousResearch/hermes-agent · 16 tokens

agent-v3-memory-specialist

Agent skill for v3-memory-specialist - invoke with $agent-v3-memory-specialist.

ruvnet/ruflo · 25 tokens

langchain

Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct agents, tool calling, memory management, and vector store retrieval. Use for building chatbots, question-answering systems, autonomous agents, or RAG…

davila7/claude-code-templates · 79 tokens

cognee-cli

Use when the user wants to drive cognee from the terminal with cognee-cli — remember/recall/forget/improve memory commands, managing datasets and config, or database migrations.

topoteretes/cognee · 42 tokens

mem0-integration

Mem0 memory layer integration for AI agents. Implement persistent, semantic memory for long-term context retention and personalization.

a5c-ai/babysitter · 27 tokens