[{"data":1,"prerenderedAt":4},["ShallowReactive",2],{"readme:evoontology":3},"\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fruc-datalab\u002Fevoontology\u002FHEAD\u002Fassets\u002Flogo.png\" alt=\"EvoOntology\" width=\"68%\" \u002F>\n\u003C\u002Fp>\u003Ch1>EvoOntology: A Self-Evolving Ontology Layer for Data Agents\u003C\u002Fh1>\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2609.15779\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FarXiv-2609.15779-b31b1b.svg?logo=arXiv\" alt=\"arXiv\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fruc-datalab\u002FEvoOntology\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FMCP-compatible-7c3aed.svg\" alt=\"MCP compatible\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fruc-datalab\u002FEvoOntology\u002Ftree\u002Fmaster\u002Fplugins\u002Fevoontology-codex\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPlug--in-codex-white.svg\" alt=\"Codex plugin\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fruc-datalab\u002FEvoOntology\u002Ftree\u002Fmaster\u002Fplugins\u002Fclaude-code\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FPlug--in-claude--code-orange.svg\" alt=\"Claude Code plugin\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fruc-datalab\u002FEvoOntology\u002Fstargazers\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fruc-datalab\u002FEvoOntology?style=flat&logo=github&color=3941EA\" alt=\"GitHub stars\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fruc-datalab\u002FEvoOntology\u002Fforks\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fforks\u002Fruc-datalab\u002FEvoOntology?style=flat&logo=github&color=3941EA\" alt=\"GitHub forks\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fhitscounter.dev\u002Fhistory?url=https%3A%2F%2Fgithub.com%2Fruc-datalab%2FEvoOntology\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fhitscounter.dev\u002Fapi\u002Fhit?url=https%3A%2F%2Fgithub.com%2Fruc-datalab%2FEvoOntology&label=Views&icon=graph-up&color=%233941ea&message=&style=flat&tz=Asia%2FShanghai\" alt=\"Page views: today \u002F total\" \u002F>\u003C\u002Fa>\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fruc-datalab\u002Fevoontology\u002Fblob\u002FHEAD\u002Fassets\u002Fwecom.jpg\" rel=\"nofollow ugc noopener\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FWeCom-%E5%8A%A0%E5%85%A5Data%2BAI%E4%BA%A4%E6%B5%81%E7%BE%A4-black?logo=wechat&logoColor=07C160\" alt=\"Join the Data+AI Enterprise WeChat group\" \u002F>\u003C\u002Fa>\n\u003C\u002Fp>\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fruc-datalab\u002Fevoontology\u002Fblob\u002FHEAD\u002FREADME.md\" rel=\"nofollow ugc noopener\">\u003Cstrong>English\u003C\u002Fstrong>\u003C\u002Fa> | \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fruc-datalab\u002Fevoontology\u002Fblob\u002FHEAD\u002FREADME.zh-CN.md\" rel=\"nofollow ugc noopener\">简体中文\u003C\u002Fa>\n\u003C\u002Fp>\u003Cblockquote>\n\u003Cp>\u003Cstrong>Authors:\u003C\u002Fstrong> \u003Ca href=\"https:\u002F\u002Fgithub.com\u002FMeiduoChong\" rel=\"nofollow ugc noopener\">Meiduo Chong\u003C\u002Fa>, \u003Ca href=\"https:\u002F\u002Fzhangshaolei1998.github.io\u002F\" rel=\"nofollow ugc noopener\">Shaolei Zhang\u003C\u002Fa>\u003Csup>*\u003C\u002Fsup>, \u003Ca href=\"https:\u002F\u002Fiir.ruc.edu.cn\u002F~fanj\u002F\" rel=\"nofollow ugc noopener\">Ju Fan\u003C\u002Fa>, \u003Ca href=\"https:\u002F\u002Finfo.ruc.edu.cn\u002Fjsky\u002Fszdw\u002Fajxjgcx\u002Fjsjkxyjsx1\u002Fjs2\u002F7374b0a3f58045fc9543703ccea2eb9c.htm\" rel=\"nofollow ugc noopener\">Xiaoyong Du\u003C\u002Fa>\u003Cbr \u002F>\nRenmin University of China\u003Cbr \u002F>\u003C\u002Fp>\n\u003C\u002Fblockquote>\n\u003Cp>EvoOntology is the first self-evolving ontology layer for data agents, aiming to bridge the \u003Cstrong>agent-data gap\u003C\u002Fstrong> over heterogeneous tables, files, and databases. It exposes a versioned \u003Cstrong>Ontology Layer through MCP tools\u003C\u002Fstrong>, grounds that layer in real workload evidence, and continuously adapts it from execution trajectories.\u003C\u002Fp>\n\u003Cul>\n\u003Cli>🔌 Universal Agent Plugin as MCP: Seamlessly integrates with Claude Code, Codex, and other AI agents.\u003C\u002Fli>\n\u003Cli>🤖 Automatic Ontology Construction: Builds a tailored ontology layer directly from your data.\u003C\u002Fli>\n\u003Cli>♻️ Continuous Self-Evolution: Continuously evolves and refines the ontology layer based on interaction history.\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Ch2>🎬 Demo\u003C\u002Fh2>\n\u003Cp>The Codex and Claude Code plugins build and evolve ontology layers over your data.\u003C\u002Fp>\n\u003Cp>\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fe15f4acd-7161-4ae1-ba41-f2f3ea05488b\" rel=\"nofollow ugc noopener\">https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002Fe15f4acd-7161-4ae1-ba41-f2f3ea05488b\u003C\u002Fa>\u003C\u002Fp>\n\u003Ch2>🧭 EvoOntology Makes Your Data Valuable!\u003C\u002Fh2>\n\u003Cul>\n\u003Cli>\u003Cstrong>Raw data leaves semantics implicit.\u003C\u002Fstrong> Table names, columns, file paths, and isolated observations rarely explain metric definitions, entity relationships, or business constraints. Agents must infer them repeatedly and are prone to semantic errors.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Static semantic layers do not scale with use.\u003C\u002Fstrong> Hand-authored layers require sustained expert maintenance, become stale as data and workloads change, and consume increasing context when injected in full.\u003C\u002Fli>\n\u003Cli>\u003Cstrong>Agents need semantics that can adapt.\u003C\u002Fstrong> EvoOntology provides a workload-grounded Ontology Layer that agents query on demand and that evolves from observed execution behavior under controlled evaluation.\u003C\u002Fli>\n\u003C\u002Ful>\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Fraw.githubusercontent.com\u002Fruc-datalab\u002Fevoontology\u002FHEAD\u002Fassets\u002Fevoontology-overview.png\" alt=\"Data Agents with and without EvoOntology\" width=\"92%\" \u002F>\n\u003C\u002Fp>\u003Cp align=\"center\">\u003Cstrong>An agent-first, self-evolving ontology layer for Data Agent\n\u003C\u002Fstrong>\u003C\u002Fp>",1790633828181]