OpenViking is an open-source context database for AI agents that stores memories, resources, and skills in a browsable virtual filesystem. Agents use it to find and load relevant context in layers while inspecting how retrieval decisions were made.
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.
git clone --depth 1 https://github.com/volcengine/OpenVikingWrote 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.
[](https://agentmods.dev/plugins/volcengine/openviking/claude-code-memory-plugin)<a href="https://agentmods.dev/plugins/volcengine/openviking/claude-code-memory-plugin"><img src="https://agentmods.dev/badge/plugins/volcengine/openviking/claude-code-memory-plugin/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/plugins/volcengine/openviking/claude-code-memory-plugin"><img src="https://agentmods.dev/badge/plugins/volcengine/openviking/claude-code-memory-plugin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
openviking-memory 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 today.
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.
The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
What it installs
The manifest is a name and a version. 1 skill, 9 hooks travel with it, and installing the plugin installs all of them — 181 tokens a session between them. Each is measured on its own page, and each can be installed alone.
- Skill ov-memory-doctor E 181 tokens
- Hook PreToolUse A not measured
- Hook PostToolUse A not measured
- Hook PreCompact A not measured
- Hook SessionEnd A not measured
- Hook SessionStart A not measured
- Hook Stop A not measured
- Hook SubagentStart A not measured
- Hook SubagentStop A not measured
- Hook UserPromptSubmit A not measured
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.
- today Changed 804e4b234a77
- 2d ago Changed · -1 lines 051d06e4fab4
- 3d ago Changed b01caf8eb9c3
- 6d ago Changed 0ab5eb713ad7
- 7d ago Changed ac2741b7bae4
- 9d ago Changed · +1 lines 2a07c8f7aa6d
- 14d ago Changed e85d58c4572b
- 15d ago Changed f30c371f40f9
- 16d ago Changed 2ffffea34814
- 21d ago First seen · 20 lines scan A 26ea707309cc
openviking-memory is a plugin published in the GitHub repository volcengine/OpenViking (40,015 stars, last pushed today), licensed AGPL-3.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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.
Other plugins, from other repositories
causal-memory
Persistent causal memory for Claude Code — decisions, outcomes, and lessons that survive compaction. Same-context counterfactuals (natural experiments), a falsifiable prediction ledger, and an activation skill that teaches when to recall and record.
l123-harness
A project structure for keeping an AI agent’s memory outside the model in three layers: persistent notes, an index, and detailed records. It also provides templates, approval controls, event logs, context-saving procedures, and weekly review tools.
deja
deja-vu memory for Gemini CLI: the coding sessions already on your disk — Gemini CLI, Claude Code, Codex, Cursor and thirty-eight more — searchable and recalled, including work from before it was installed.
knowl
Persistent memory for Claude Code. Facts are typed, sourced, and retired when they change, so a query returns the current answer rather than every answer it has ever held. Local SQLite in your repository — no API key, nothing uploaded.
memex
Zettelkasten-based agent memory system with bidirectional links.
titen-memory
Use Titen's evidence-grounded collaborative memory. The local stdio mode needs no configuration; a served Titen endpoint is the alternative for a shared store.