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.
npx agentmods add skills/djblack1209-coder/openclaw-bot/openvikingnpx skills add djblack1209-coder/OpenClaw-Bot --skill openvikinggit clone --depth 1 https://github.com/djblack1209-coder/OpenClaw-BotWrote 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/skills/djblack1209-coder/openclaw-bot/openviking)<a href="https://agentmods.dev/skills/djblack1209-coder/openclaw-bot/openviking"><img src="https://agentmods.dev/badge/skills/djblack1209-coder/openclaw-bot/openviking.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00046 | $0.00794 |
| Opus 5 | $0.00023 | $0.00397 |
| Sonnet 5 | $0.00009 | $0.00159 |
| Haiku 4.5 | $0.00005 | $0.00079 |
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 4d ago.
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.
What it actually says
OpenViking 上下文数据库
字节跳动开源的 AI Agent 上下文数据库，用文件系统范式统一管理 memory、resources、skills。
核心概念
- 虚拟文件系统: 所有上下文映射到
viking://URI，层级目录结构 - 三层按需加载:
- L0 (摘要): ~100 tokens，快速相关性判断
- L1 (概览): ~2k tokens，核心信息用于规划
- L2 (详情): 完整内容，按需加载
- 目录递归检索: 向量搜索 + 目录遍历，先定位高分目录再递归细化
- 自动会话记忆: 从对话中自动提取长期记忆
安装
pip install openviking --upgrade --force-reinstall
要求: Python 3.10+, Go 1.22+
与 OpenClaw 集成方式
1. 作为记忆后端
替代当前 SQLite memory，用 OpenViking 管理所有 agent 记忆：
# 启动 OpenViking 服务
openviking-server --port 1933
# 导入现有记忆
ov add-resource apps/openclaw/memory/
2. 作为技能索引
将 40+ skills 导入 OpenViking，实现语义检索：
ov add-resource apps/openclaw/skills/
ov find "交易风控相关的技能"
3. 作为知识库
导入项目文档、代码库、外部资料：
ov add-resource docs/
ov add-resource packages/openclaw-npm/src/
使用命令
ov ls viking://resources/ # 列出资源
ov tree viking://memory/ -L 2 # 查看记忆树
ov find "社交发布失败的处理方法" # 语义搜索
ov grep "Telegram" --uri memory # 模式搜索
对比当前 SQLite Memory
| 维度 | SQLite (当前) | OpenViking |
|---|---|---|
| 检索方式 | 需要 embedding API | 内置向量 + 目录检索 |
| Token 消耗 | 全量加载 | L0/L1/L2 按需加载，降低 83-96% |
| 上下文理解 | 扁平存储 | 层级目录，全局理解更好 |
| 自进化 | 手动维护 | 自动从会话提取记忆 |
| 调试 | 黑盒 | 可观测检索轨迹 |
触发条件
当 严总 提到以下关键词时激活:
- "openviking"、"上下文数据库"、"记忆升级"、"viking"
- "导入知识库"、"语义检索"
执行流程
- 检查 OpenViking 是否已安装 (
which ov) - 若未安装，引导 严总 执行
pip install openviking - 启动服务并导入指定资源
- 配置 OpenClaw gateway 使用 OpenViking 作为记忆后端
- 验证检索功能正常
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.
- 4d ago First seen · 93 lines · 46 tokens per session scan A 6833c8517518
openviking is a skill published in the GitHub repository djblack1209-coder/OpenClaw-Bot (5 stars, last pushed yesterday), licensed Apache-2.0. It adds 46 tokens to every session and 794 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
transcribe-filing
Transcribe an insurance rate filing or internal rating manual into an OpenRater workbook, then validate, build, verify, and rate it through the OpenRater MCP tools. Use when the user shares a filing/manual (PDF or pages) and wants it executable — "build this filing", "digitize this rating manual", "make this rateable"…
metrics-instrumentation
Specification for instrumenting an opik-backend workflow with operational OpenTelemetry metrics — per-stage throughput/latency/error counters and native histograms, dimensioned per-customer (workspace). Use when a pipeline (scoring, ingestion, experiments, jobs) needs per-stage visibility. Covers metric emission only…
notifications
Send notifications through the unified notification router.
telegram-setup
Connect a Telegram bot to the Vellum Assistant gateway with automated webhook registration and credential storage.
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…
prompt-engineer
Prompt engineering expert for chain-of-thought, few-shot learning, evaluation, and LLM optimization.