面向企业级市场的全方位 AI 应用开发框架，支持多厂商大模型统一接入和管理，具备安全可控的企业知识库和高精度检索优化能力，提供可视化流程编排、自主决策智能体和多智能体协同调度，兼容主流 Agent Skill 协议，帮助企业和开发者零门槛快速构建安全、高效、可落地的 AI 智能体应用和行业解决方案。
面向企业级市场的全方位 AI 应用开发框架，支持多厂商大模型统一接入和管理，具备安全可控的企业知识库和高精度检索优化能力，提供可视化流程编排、自主决策智能体和多智能体协同调度，兼容主流 Agent Skill 协议，帮助企业和开发者零门槛快速构建安全、高效、可落地的 AI 智能体应用和行业解决方案。
This project provides two Docker deployment methods:
Use docker-compose-all.yaml to start all services at once (including backend, admin panel, user frontend, and dependencies):
…
If you are using Windows with Docker Desktop, you can use PowerShell to execute the following commands:
…
The default Compose file also publishes MySQL (23306), Redis (26379),
Weaviate (28080), and MinIO (29000/29090). For production deployments,
change the default MySQL and MinIO passwords and expose only the application
ports through the firewall or a reverse proxy.
To upgrade to another published release, update RUIYI_VERSION in
docs/docker/ruoyi-ai/.env, then run docker compose pull and
docker compose up -d with the same --env-file and -f options. Do not use
docker compose down -v unless you intend to delete persistent data volumes.
If you need to build backend services from source, follow these steps:
# Enter backend project directory
cd ruoyi-ai
# Start backend service (build from source)
docker-compose up -d --build
# Wait for backend service to start
docker-compose logs -f backend
# Enter admin panel project directory
cd ruoyi-admin
# Build and start admin panel
docker-compose up -d --build
# Access admin panel
# URL: http://localhost:5666
# Enter user frontend project directory
cd ruoyi-web
# Build and start user frontend
docker-compose up -d --build
# Access user frontend
# URL: http://localhost:5137
Want to learn more about installation, deployment, configuration, and secondary development?
We warmly welcome community contributions! Whether you are a seasoned developer or just getting started, you can contribute to the project
git checkout -b feature/new-feature-name)git commit -m 'Add new feature')git push origin feature/new-feature-name)Tip: We recommend submitting PRs to GitHub, we will automatically sync to other code hosting platforms
This project is licensed under the MIT License. See the LICENSE file for details.
Thanks to the following excellent open-source projects for their support:
Thanks to the following sponsors for supporting this project:
Visit Atlas Cloud · Coding Plan Promotion A full-modal AI inference platform that gives developers a unified AI API, supporting video generation, image generation, and LLMs. Connect once to access 300+ curated models.
Sign up to claim 25 million tokens — go now Enjoy ByteDance's in-house Doubao models plus full-power open-source SOTA models, covering text, VLM, and image generation — all modalities in one stop: Seed-2.1, Seedream-5.0, GLM-5.2, DeepSeek, and more. Not just for coding — it can also tackle complex long-horizon Agent tasks!
暂无开放 Issues，或尚未同步最近议题。