Yuxi - A Multi-tenant Harness Platform Combining Knowledge Bases and Knowledge Graphs

[![](https://img.shields.io/badge/Docker-2496ED?style=flat&logo=docker&logoColor=ffffff)](https://github.com/xerrors/Yuxi/blob/main/docker-compose.yml) [![](https://img.shields.io/github/issues/xerrors/Yuxi?color=F48D73)](https://github.com/xerrors/Yuxi/issues) [![License](https://img.shields.io/github/license/bitcookies/winrar-keygen.svg?logo=github)](https://github.com/xerrors/Yuxi/blob/main/LICENSE) [![DeepWiki](https://img.shields.io/badge/DeepWiki-blue.svg)](https://deepwiki.com/xerrors/Yuxi) [![zread](https://img.shields.io/badge/Ask_Zread-_.svg?style=flat&color=00b0aa&labelColor=000000&logo=data%3Aimage%2Fsvg%2Bxml%3Bbase64%2CPHN2ZyB3aWR0aD0iMTYiIGhlaWdodD0iMTYiIHZpZXdCb3g9IjAgMCAxNiAxNiIgZmlsbD0ibm9uZSIgeG1sbnM9Imh0dHA6Ly93d3cudzMub3JnLzIwMDAvc3ZnIj4KPHBhdGggZD0iTTQuOTYxNTYgMS42MDAxSDIuMjQxNTZDMS44ODgxIDEuNjAwMSAxLjYwMTU2IDEuODg2NjQgMS42MDE1NiAyLjI0MDFWNC45NjAxQzEuNjAxNTYgNS4zMTM1NiAxLjg4ODEgNS42MDAxIDIuMjQxNTYgNS42MDAxSDQuOTYxNTZDNS4zMTUwMiA1LjYwMDEgNS42MDE1NiA1LjMxMzU2IDUuNjAxNTYgNC45NjAxVjIuMjQwMUM1LjYwMTU2IDEuODg2NjQgNS4zMTUwMiAxLjYwMDEgNC45NjE1NiAxLjYwMDFaIiBmaWxsPSIjZmZmIi8%2BCjxwYXRoIGQ9Ik00Ljk2MTU2IDEwLjM5OTlIMi4yNDE1NkMxLjg4ODEgMTAuMzk5OSAxLjYwMTU2IDEwLjY4NjQgMS42MDE1NiAxMS4wMzk5VjEzLjc1OTlDMS42MDE1NiAxNC4xMTM0IDEuODg4MSAxNC4zOTk5IDIuMjQxNTYgMTQuMzk5OUg0Ljk2MTU2QzUuMzE1MDIgMTQuMzk5OSA1LjYwMTU2IDE0LjExMzQgNS42MDE1NiAxMy43NTk5VjExLjAzOTlDNS42MDE1NiAxMC42ODY0IDUuMzE1MDIgMTAuMzk5OSA0Ljk2MTU2IDEwLjM5OTlaIiBmaWxsPSIjZmZmIi8%2BCjxwYXRoIGQ9Ik0xMy43NTg0IDEuNjAwMUgxMS4wMzg0QzEwLjY4NSAxLjYwMDEgMTAuMzk4NCAxLjg4NjY0IDEwLjM5ODQgMi4yNDAxVjQuOTYwMUMxMC4zOTg0IDUuMzEzNTYgMTAuNjg1IDUuNjAwMSAxMS4wMzg0IDUuNjAwMUgxMy43NTg0QzE0LjExMTkgNS42MDAxIDE0LjM5ODQgNS4zMTM1NiAxNC4zOTg0IDQuOTYwMVYyLjI0MDFDMTQuMzk4NCAxLjg4NjY0IDE0LjExMTkgMS42MDAxIDEzLjc1ODQgMS42MDAxWiIgZmlsbD0iI2ZmZiIvPgo8cGF0aCBkPSJNNCAxMkwxMiA0TDQgMTJaIiBmaWxsPSIjZmZmIi8%2BCjxwYXRoIGQ9Ik00IDEyTDEyIDQiIHN0cm9rZT0iI2ZmZiIgc3Ryb2tlLXdpZHRoPSIxLjUiIHN0cm9rZS1saW5lY2FwPSJyb3VuZCIvPgo8L3N2Zz4K&logoColor=ffffff)](https://zread.ai/xerrors/Yuxi) [![demo](https://img.shields.io/badge/demo-00A1D6.svg?style=flat&logo=bilibili&logoColor=white)](https://www.bilibili.com/video/BV1DF14BTETq/) xerrors%2FYuxi | Trendshift [[Docs]](https://xerrors.github.io/Yuxi) · [[中文]](README.md)
![arch](https://xerrors.oss-cn-shanghai.aliyuncs.com/github/gpt-iamge-2-arch.png) **Image generated by GPT-Image-2.* ## Core Features - **Agent development**: Built on LangGraph, with support for sub-agents, Skills, MCPs, Tools, and middleware. - **Knowledge base (RAG)**: Multi-format document parsing, Embedding / Rerank configuration, and knowledge base evaluation. - **Knowledge graph**: Graph construction and visualization based on LightRAG, with property graph support for agent reasoning. - **Platform and engineering**: Vue + FastAPI architecture with dark mode, Docker-based development, and production-oriented deployment. ## Quick Start Clone the repository and initialize the project: ```bash git clone --branch v0.6.2 --depth 1 https://github.com/xerrors/Yuxi.git cd Yuxi # Linux/macOS ./scripts/init.sh # Windows PowerShell .\scripts\init.ps1 ``` Start the project with Docker: ```bash docker compose up --build ``` After the services are ready, open `http://localhost:5173`. ## Examples and Demo
Home
Home 		Dashboard statistics
Dashboard Statistics
Agent configuration
Agent Configuration 		Knowledge base invocation
Knowledge Base Invocation
Create knowledge base
Create Knowledge Base 		Knowledge base management
Knowledge Base Management
Knowledge graph
Knowledge Graph Visualization 		Project docs
Project Documentation
Skills management
Extension Management (Skills) 		MCPs management
Extension Management (MCPs)
User and department permissions
User / Department Permission Management 		Model provider configuration
Model Provider Configuration
## Acknowledgements Yuxi references and builds on the following excellent open-source projects: - [LightRAG](https://github.com/HKUDS/LightRAG) - Used as the foundation for graph construction and retrieval. - [DeepAgents](https://github.com/langchain-ai/deepagents) - Used as the deep agent framework. - [DeerFlow](https://github.com/bytedance/deer-flow) - Referenced for Sandbox agent architecture ideas. - [RAGflow](https://github.com/infiniflow/ragflow) - Referenced for document text chunking strategies. - [LangGraph](https://github.com/langchain-ai/langgraph) - Multi-agent orchestration framework and the core architectural foundation of this project. - [QwenPaw](https://github.com/agentscope-ai/QwenPaw) - Referenced for model configuration and personal file area design. ## Contributing Thanks to all contributors for supporting this project! ## Star History [![Star History Chart](https://api.star-history.com/svg?repos=xerrors/Yuxi)](https://star-history.com/#xerrors/Yuxi) ## 📄 License This project is licensed under the MIT License. See [LICENSE](LICENSE) for details. ---
**If this project helps you, please give us a ⭐️.**