[{"data":1,"prerenderedAt":4},["ShallowReactive",2],{"readme:openviking":3},"\u003Cdiv align=\"center\">\u003Ca href=\"https:\u002F\u002Fopenviking.ai\u002F\" rel=\"nofollow ugc noopener\">\n  \u003Cpicture>\n    \u003Cimg alt=\"OpenViking\" src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fvolcengine\u002Fopenviking\u002FHEAD\u002Fdocs\u002Fimages\u002Fov-logo.png\" width=\"200px\" height=\"auto\" \u002F>\n  \u003C\u002Fpicture>\n\u003C\u002Fa>\u003Ch3>OpenViking: The Context Database for AI Agents\u003C\u002Fh3>\n\u003Cp>English \u002F \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fvolcengine\u002Fopenviking\u002Fblob\u002FHEAD\u002FREADME_CN.md\" rel=\"nofollow ugc noopener\">中文\u003C\u002Fa> \u002F \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fvolcengine\u002Fopenviking\u002Fblob\u002FHEAD\u002FREADME_JA.md\" rel=\"nofollow ugc noopener\">日本語\u003C\u002Fa>\u003C\u002Fp>\n\u003Cp>\u003Ca href=\"https:\u002F\u002Fwww.openviking.ai\" rel=\"nofollow ugc noopener\">Website\u003C\u002Fa> · \u003Ca href=\"https:\u002F\u002Fopenviking.ai\u002Fstudio\" rel=\"nofollow ugc noopener\">Live Demo\u003C\u002Fa> · \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fvolcengine\u002FOpenViking\" rel=\"nofollow ugc noopener\">GitHub\u003C\u002Fa> · \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fvolcengine\u002FOpenViking\u002Fissues\" rel=\"nofollow ugc noopener\">Issues\u003C\u002Fa> · \u003Ca href=\"https:\u002F\u002Fdocs.openviking.ai\u002F\" rel=\"nofollow ugc noopener\">Docs\u003C\u002Fa>\u003C\u002Fp>\n\u003Cp>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fvolcengine\u002FOpenViking\u002Freleases\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fv\u002Frelease\u002Fvolcengine\u002FOpenViking?color=369eff&labelColor=black&logo=github&style=flat-square\" alt=\"\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fvolcengine\u002FOpenViking\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fvolcengine\u002FOpenViking?labelColor&style=flat-square&color=ffcb47\" alt=\"\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fvolcengine\u002FOpenViking\u002Fissues\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fissues\u002Fvolcengine\u002FOpenViking?labelColor=black&style=flat-square&color=ff80eb\" alt=\"\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fvolcengine\u002FOpenViking\u002Fgraphs\u002Fcontributors\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fcontributors\u002Fvolcengine\u002FOpenViking?color=c4f042&labelColor=black&style=flat-square\" alt=\"\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fvolcengine\u002FOpenViking\u002Fblob\u002Fmain\u002FLICENSE\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-AGPLv3-white?labelColor=black&style=flat-square\" alt=\"\" \u002F>\u003C\u002Fa>\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fvolcengine\u002FOpenViking\u002Fcommits\u002Fmain\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flast-commit\u002Fvolcengine\u002FOpenViking?color=c4f042&labelColor=black&style=flat-square\" alt=\"\" \u002F>\u003C\u002Fa>\u003C\u002Fp>\n\u003Cp>👋 Join our Community\u003C\u002Fp>\n\u003Cp>📱 \u003Ca href=\"https:\u002F\u002Fdocs.openviking.ai\u002Fen\u002Fabout\u002F01-about-us#lark-group\" rel=\"nofollow ugc noopener\">Lark Group\u003C\u002Fa> · \u003Ca href=\"https:\u002F\u002Fdocs.openviking.ai\u002Fen\u002Fabout\u002F01-about-us#wechat-group\" rel=\"nofollow ugc noopener\">WeChat\u003C\u002Fa> · \u003Ca href=\"https:\u002F\u002Fdiscord.com\u002Finvite\u002FeHvx8E9XF3\" rel=\"nofollow ugc noopener\">Discord\u003C\u002Fa> · \u003Ca href=\"https:\u002F\u002Fx.com\u002Fopenvikingai\" rel=\"nofollow ugc noopener\">X\u003C\u002Fa>\u003C\u002Fp>\n\u003Cp>\u003Ca href=\"https:\u002F\u002Ftrendshift.io\u002Frepositories\u002F19668\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Ftrendshift.io\u002Fapi\u002Fbadge\u002Frepositories\u002F19668\" alt=\"volcengine%2FOpenViking | Trendshift\" width=\"250\" height=\"55\" \u002F>\u003C\u002Fa>\u003C\u002Fp>\n\u003C\u002Fdiv>\u003Chr \u002F>\n\u003Ch2>What is OpenViking\u003C\u002Fh2>\n\u003Cp>OpenViking is an open-source context database for AI agents. It stores memories, resources, and skills as one virtual filesystem under the \u003Ccode>viking:\u002F\u002F\u003C\u002Fcode> protocol, so an agent browses its own context with \u003Ccode>ls\u003C\u002Fcode>, \u003Ccode>tree\u003C\u002Fcode>, and \u003Ccode>find\u003C\u002Fcode> 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: \u003Ca href=\"https:\u002F\u002Fdocs.openviking.ai\u002Fen\u002Fgetting-started\u002F01-introduction\" rel=\"nofollow ugc noopener\">Getting started\u003C\u002Fa>.\u003C\u002Fp>\n\u003Cp>\u003Ca href=\"https:\u002F\u002Fopenviking.ai\u002Fstudio\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fvolcengine\u002Fopenviking\u002FHEAD\u002Fdocs\u002Fimages\u002Fstudio-playground.png\" alt=\"OpenViking Studio playground\" \u002F>\u003C\u002Fa>\u003C\u002Fp>\n\u003Cp>\u003Cem>The \u003Ca href=\"https:\u002F\u002Fopenviking.ai\u002Fstudio\" rel=\"nofollow ugc noopener\">OpenViking Studio\u003C\u002Fa> playground — a live demo you can open in the browser, no installation required.\u003C\u002Fem>\u003C\u002Fp>\n\u003Ch2>Why OpenViking\u003C\u002Fh2>\n\u003Cul>\n\u003Cli>\u003Cstrong>One filesystem for all context.\u003C\u002Fstrong> Memories, resources, and skills each get a \u003Ccode>viking:\u002F\u002F\u003C\u002Fcode> URI. Agents locate and manipulate context deterministically, like a developer working with files. → \u003Ca href=\"https:\u002F\u002Fdocs.openviking.ai\u002Fen\u002Fconcepts\u002F04-viking-uri\" rel=\"nofollow ugc noopener\">Viking URI\u003C\u002Fa> · \u003Ca href=\"https:\u002F\u002Fdocs.openviking.ai\u002Fen\u002Fconcepts\u002F02-context-types\" rel=\"nofollow ugc noopener\">Context types\u003C\u002Fa>\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Tiered loading cuts token spend.\u003C\u002Fstrong> Every entry is processed into L0 (abstract), L1 (overview), and L2 (details) on write, then loaded only as deep as the task requires. → \u003Ca href=\"https:\u002F\u002Fdocs.openviking.ai\u002Fen\u002Fconcepts\u002F03-context-layers\" rel=\"nofollow ugc noopener\">Context layers\u003C\u002Fa>\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Directory recursive retrieval.\u003C\u002Fstrong> Vector search first locates the highest-scoring directory, then drills down layer by layer, so results arrive with their surrounding context intact. → \u003Ca href=\"https:\u002F\u002Fdocs.openviking.ai\u002Fen\u002Fconcepts\u002F07-retrieval\" rel=\"nofollow ugc noopener\">Retrieval\u003C\u002Fa>\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Observable retrieval.\u003C\u002Fstrong> Each query preserves its directory-browsing trajectory. When a result looks wrong, you can see exactly which path produced it. → [Retrieval](\u003Ca href=\"https:\u002F\u002Fdocs.openviking.ai\u002Fen\u002F\" rel=\"nofollow ugc noopener\">https:\u002F\u002Fdocs.openviking.ai\u002Fen\u002F\u003C\u002Fa>\u003C\u002Fli>\n\u003C\u002Ful>\n",1787445490529]