ageerle/ruoyi-ai

An enterprise AI development framework for building AI agents. It provides unified management of multi-provider LLMs, secure enterprise knowledge bases with...

View on GitHub ↗Jump to charts ↓

Summary Information

Updated 45 minutes ago
Added to GitGenius on September 11th, 2026
Created on January 16th, 2024
Open Issues & Pull Requests: 8 (+0)
GitHub issues: Enabled
Number of forks: 1,403
Total Stargazers: 5,691 (+0)
Total Subscribers: 43 (+0)

Repository Insights (GitGenius)

Median issue/PR response: 6.2 days
Mean response time: 30.3 days
90th percentile: 91.1 days
Tracked items: 147

How this project is maintained

Around half of the issues opened in the past year never receive a reply. Only 17% of issues opened in the past year have been closed. Three people close 87% of everything that gets resolved.

Charts & Analytics

Fetching additional details & charts...

Issue Activity (beta)

Open issues: 5
New in 7 days: 3
Closed in 7 days: 4
Avg open age: 47 days
Stale 30+ days: 2
Stale 90+ days: 0

Recent activity

Opened in 7 days: 3
Closed in 7 days: 1
Comments in 7 days: 0
Events in 7 days: 1

Top labels

  • bug (11)
  • enhancement (6)

Detailed Description

RuoYi AI is an enterprise-grade AI development framework for building and orchestrating AI agents with multi-provider language model support and advanced retrieval-augmented generation capabilities.

The framework addresses the complexity of building production-ready AI systems by providing unified management across multiple LLM providers, secure knowledge base integration with high-precision retrieval, and visual workflow design. It uses Langchain4j as its agent foundation and supports Supervisor mode orchestration to coordinate multiple agents with flexible decision models. The tool ecosystem integrates the MCP protocol standard alongside extensible skills, while the knowledge management layer combines local RAG with vector database options including Milvus, Weaviate, and Qdrant for document-backed retrieval.

Organizations building multi-agent systems or requiring enterprise knowledge base integration should consider this framework. It suits teams needing visual workflow orchestration without code, those managing multiple LLM providers simultaneously, and projects requiring document parsing and semantic search. The platform includes admin and user-facing interfaces alongside integration with external platforms like Coze, DIFY, FastGPT, and RAGFlow, making it suitable for teams wanting a complete stack rather than building components separately.

The project maintains active development across multiple repositories covering backend services, frontend applications, and specialized modules. The codebase is written in Java and includes comprehensive documentation with live demonstration environments available for evaluation.