Yuxi
A multi-tenant agent platform combining RAG and knowledge graphs
Make enterprise knowledge retrievable, reasoned over, and deliverable by agents
[](https://github.com/xerrors/Yuxi/blob/main/docker-compose.yml)
[](https://github.com/xerrors/Yuxi/issues)
[](https://github.com/xerrors/Yuxi/blob/main/LICENSE)
[](https://deepwiki.com/xerrors/Yuxi)
[](https://zread.ai/xerrors/Yuxi)
[](https://www.bilibili.com/video/BV1TZEx6NEit/)
[[Docs]](https://xerrors.github.io/Yuxi) · [[中文]](README.md)
**Image generated by GPT-Image-2.*
## Introduction
Yuxi is an LLM-powered platform for building knowledge-base and knowledge-graph agents. It unifies **RAG retrieval**, **Milvus-backed in-knowledge-base graphs**, and **LangGraph multi-agent orchestration** into a single multi-tenant workspace: administrators configure knowledge bases, models, and permissions, while users chat — in a ChatGPT-like interface — with agents that can mount Skills, MCPs, sub-agents, and sandbox tools, and receive answers with cited sources, graph-based reasoning, and deliverable artifacts.
Navigation: [Introduction](https://xerrors.github.io/Yuxi/) ｜ [Quick Start](https://xerrors.github.io/Yuxi/intro/quick-start) ｜ [Roadmap](https://xerrors.github.io/Yuxi/develop-guides/roadmap); for the latest updates, see the [changelog](https://xerrors.github.io/Yuxi/develop-guides/changelog).
## Core Features
- 🤖 **Agent development** — Built on LangGraph, with sub-agents (SubAgents), Skills, MCPs, Tools, and middleware; long-running tasks run asynchronously on a background worker, backed by a sandbox file system for persisting, previewing, and downloading tool artifacts.
- 📚 **Knowledge base (RAG)** — Multi-format document parsing (MinerU / PaddleX / OCR), configurable Embedding and Rerank models, knowledge base evaluation, in-app PDF / image preview, and retrieval sources backfilled as chat citations.
- 🕸️ **Knowledge graph** — Build, visualize, and retrieve entity-relation graphs inside Milvus knowledge bases, then fuse graph hits with chunk retrieval for agent reasoning.
- 🏢 **Multi-tenancy & permissions** — User / department-level access control, unified model provider configuration, and API Key authentication for external system integration.
- ⚙️ **Platform & engineering** — Vue + FastAPI architecture, ready-to-run Docker Compose deployment, dark mode, a lightweight LITE startup mode, and production-grade orchestration.
## Tech Stack
| Layer | Technologies |
| --- | --- |
| Frontend | Vue 3 · Vite · Pinia |
| Backend | FastAPI · LangGraph · ARQ (async worker) |
| Storage | PostgreSQL · Redis · MinIO · Milvus · Neo4j |
| Doc parsing | MinerU · PaddleX · RapidOCR |
| Deployment | Docker Compose |
## Quick Start
**Prerequisites**: [Docker](https://docs.docker.com/get-docker/) and Docker Compose installed, plus at least one OpenAI-compatible LLM API.
**1. Clone and initialize**
```bash
git clone --branch v0.7.1.beta1 --depth 1 https://github.com/xerrors/Yuxi.git
cd Yuxi
# Linux/macOS
./scripts/init.sh
# Windows PowerShell
.\scripts\init.ps1
```
**2. Start with Docker**
```bash
docker compose up --build
```
**3. Open the platform**
Once the services are ready, open `http://localhost:5173` in your browser and sign in with the admin account generated during initialization.
> 💡 If you don't need heavy dependencies like knowledge bases / graphs, run `make up-lite` for a lightweight LITE mode with faster cold starts. See the [docs](https://xerrors.github.io/Yuxi) for more deployment details.
## Examples and Demo
