Yuxi MCP Server
xerrors/Yuxi
可私有部署的多租户知识智能体平台:统一 RAG、知识图谱、多智能体、MCP/Skills、沙盒与权限管理。Yuxi = Cloud Agents + Knowledge RAG, Self-hosted knowledge agent platform for RAG, knowledge graphs and multi-agent workflows.
claude mcp add agentrank -- npx -y agentrank-mcp-server Overview
xerrors/Yuxi is a Python tool licensed under MIT. 可私有部署的多租户知识智能体平台:统一 RAG、知识图谱、多智能体、MCP/Skills、沙盒与权限管理。Yuxi = Cloud Agents + Knowledge RAG, Self-hosted knowledge agent platform for RAG, knowledge graphs and multi-agent workflows. Topics: docker, kbqa, kgqa, llms, neo4j, rag, vue, fastapi, harness, agentic-rag, ai-agents, deepagents, document-ai, knowledge-base, knowledge-graph, langgraph, mcp, milvus, multi-agent, self-hosted.
Ranked #62 out of 24840 indexed tools.
In the top 1% of all indexed tools.
Has 7,204 GitHub stars.
Has 60 contributors.
Actively maintained with commits in the last week.
Ecosystem
Score Breakdown
7,204 stars → well-known project
Last commit today → actively maintained
562/647 issues closed → responsive maintainer
60 contributors → active community
No dependents → no downstream usage
Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →
Matched Queries
From the README
**Yuxi = Cloud Agents + Knowledge RAG**,Yuxi 是一个可私有部署的多租户知识智能体平台。自定义智能体,权限可控,沉淀企业轨迹。它把知识库检索、知识图谱、LangGraph 多智能体编排、MCP/Skills、沙盒工具和权限管理放进同一个工作区。让每个用户都拥有一个云端 Codex。 [项目主页](https://xerrors.github.io/Yuxi/) · [快速开始](https://xerrors.github.io/Yuxi/intro/quick-start) · [演示视频](https://www.bilibili.com/video/BV1erE26iEgv/) · [版本记录](https://github.com/xerrors/Yuxi/releases) · [English](README.en.md) <a href="https://trendshift.io/repositories/24335" target="_blank"></a> ## Yuxi 能做什么 Yuxi 是面向需要企业自部署的多用户 Agent 产品,且需要自己掌握数据、模型和权限的团队: - **Harness**:功能完善的云端多用户 Harness,自定义智能体,沉淀企业轨迹。 - **Knowledge**: 高效、精准的 Agentic RAG 套件,上传文档,解析、分块和向量索引。 - **执行多步骤任务**:组合工具、MCP、Skills、子智能体和沙盒,产出可预览、可下载的文件。 - **连接知识图谱**:从 Milvus 知识库的文档块中抽取实体和关系,写入 Neo4j 并参与检索。 - **管理团队使用范围**:按用户、部门和共享范围管理知识库、智能体、Skills 和模型。 - **对比运行质量**:评估知识库的检索结果,也可以用 Langfuse Dataset 评估完整智能体任务。 ## 赞助商 | 赞助商 | 介绍 | | :---: | :--- | | | Fluxion AI面向个人开发者、技术团队与企业,通过统一API接入并管理全球主流AI模型;通过多线路动态调度提升可用性,模型表现、响应时间与费用透明可查。根据不同模型与线路,API调用成本较官方或基准价格可降低4Read full README on GitHub →
Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.