Skip to content
Back to skills

Openviking

ASecurity

Manage agent memory, knowledge, and context hierarchy using OpenViking's virtual filesystem (viking://). Use when structuring multi-tier agent context, managing persistent memory across sessions, or integrating agent filesystem RAG.

  • 3 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 11, 2026
ai-agentspythonbashgitdatabasedocumentation

Security analysis

A100/100

Pro scans all 4 files and shows the line behind each finding

Scanned November 11, 2026

npx -y skills add siddu1004/SFP --skill openviking --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Openviking?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Openviking
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/siddu1004-openviking/badge)](https://www.skillsdirectory.com/skills/siddu1004-openviking)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: openviking
description: "Manage agent memory, knowledge, and context hierarchy using OpenViking's virtual filesystem (viking://). Use when structuring multi-tier agent context, managing persistent memory across sessions, or integrating agent filesystem RAG."
---

> **This skill needs OpenViking, which is installed separately.** From this skill's folder, run `python3 scripts/sfp_app.py status` to see whether it is installed and running. If it is not, run `python3 scripts/sfp_app.py install` to get the plan (it changes nothing), tell the user what it will do, and run it again with `--yes` only after they agree. `start` runs it when it is installed but stopped.

# OpenViking Context Filesystem

Structure agent memory, persistent project context, and knowledge bases using OpenViking (`volcengine/OpenViking`). OpenViking organizes agent context into a transparent, navigable virtual filesystem (`viking://`), providing multi-tier hierarchical context delivery (L0/L1/L2) to prevent context window bloat.

## Use This Skill When

- Managing long-term memory and session context across multiple agent runs.
- Navigating project knowledge graphs through standard filesystem semantics (`ls`, `cat`, `grep`).
- Integrating hierarchical RAG that loads high-level summaries first, fetching deep detail on demand.

## Core Concepts

- `viking://session/`: Current session memories and short-term dialogue buffer.
- `viking://project/`: Architectural decisions, code maps, conventions, and dependencies.
- `viking://skills/`: On-demand executable procedures and operational checklists.

## Usage & Operations

```bash
# Inspect agent virtual filesystem structure
viking ls viking://project/architecture

# Retrieve L0 summary (low-token overview)
viking cat --level=0 viking://project/overview

# Query memory with semantic search
viking search "database migration strategy"
```

## Checks & Verification

- [ ] Confirm hierarchical depth (L0 overview vs L2 full source) matches current agent task budget.
- [ ] Ensure stale session memories are pruned or compressed periodically.

## Sources

- [OpenViking Documentation](https://openviking.ai/)
- [OpenViking GitHub Repository](https://github.com/volcengine/OpenViking)

Files in this skill

  • LICENSE69 B
  • SKILL.md2.2 KB
  • scripts/app.json613 B
  • scripts/sfp_app.py10.1 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

View all in ai-agents →

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.