项目简介
OpenViking 以 viking:// 虚拟文件系统统一存储记忆、资源与技能，将内容划分为 L0/L1/L2 三层并按需加载。支持可观测的检索轨迹，帮助 AI 智能体高效管理长期记忆与知识。
README 预览
\n\n\n \n \n \n\n\n### OpenViking: The Context Database for AI Agents\n\nEnglish / [中文](README_CN.md) / [日本語](README_JA.md)\n\nWebsite · Live Demo · GitHub · Issues · Docs\n\n[](https://github.com/volcengine/OpenViking/releases)\n[](https://github.com/volcengine/OpenViking)\n[](https://github.com/volcengine/OpenViking/issues)\n[](https://github.com/volcengine/OpenViking/graphs/contributors)\n[](https://github.com/volcengine/OpenViking/blob/main/LICENSE)\n[](https://github.com/volcengine/OpenViking/commits/main)\n\n👋 Join our Community\n\n📱 Lark Group · WeChat · Discord · X\n\n\n\n\n\n***\n\n## What is OpenViking\n\nOpenViking is an open-source context database for AI agents. It stores memories, resources, and skills as one virtual filesystem under the `viking://` protocol, so an agent browses its own context with `ls`, `tree`, and `find` instead of querying a black-box vector store. Content is processed into three tiers — L0 abstract, L1 overview, L2 details — and loaded on demand. Every retrieval leaves a trajectory you can watch and debug. Full introduction: [Getting started](https://docs.openviking.ai/en/getting-started/01-introduction).\n\n[](https://openviking.ai/studio)\n\n*The [OpenViking Studio](https://openviking.ai/studio) playground — a live demo you can open in the browser, no installation required.*\n\n## Why OpenViking\n\n- **One filesystem for all context.** Memories, resources, and skills each get a `viking://` URI. Agents locate and manipulate context deterministically, like a developer working with files. → [Viking URI](https://docs.openviking.ai/en/concepts/04-viking-uri) · [Context types](https://docs.openviking.ai/en/concepts/02-context-types)\n- **Tiered loading cuts token spend.** Every entry is processed into L0 (abstract), L1 (overview), and L2 (details) on write, then loaded only as deep as the task requires. → [Context layers](https://docs.openviking.ai/en/concepts/03-context-layers)\n- **Directory recursive retrieval.** Vector sear