Yu AI Agent
编程导航 2025 年 AI 开发实战新项目，基于 Spring Boot 3 + Java 21 + Spring AI 构建 AI 恋爱大师应用和 ReAct 模式自主规划智能体YuManus，覆盖 AI 大模型接入、Spring AI 核心特性、Prompt 工程和优化、RAG 检索增强、向量数据库、Tool Calling 工具调用、MCP 模型上下文协议、AI Agent 开发（Manas Java 实现）、Cursor AI 工具等核心知识。用一套教程将程序员必知必会的 AI 技术一
What is Yu AI Agent?
Yu AI Agent is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 编程导航 2025 年 ai 开发实战新项目，基于 spring boot 3 + java 21 + spring ai 构建 ai 恋爱大师应用和 react 模式自主规划智能体yumanus，覆盖 ai 大模型接入、spring ai 核心特性、prompt 工程和优化、rag 检索增强、向量数据库、tool calling 工具调用、mcp 模型上下文协议、ai agent 开发（mana...
编程导航 2025 年 AI 开发实战新项目，基于 Spring Boot 3 + Java 21 + Spring AI 构建 AI 恋爱大师应用和 ReAct 模式自主规划智能体YuManus，覆盖 AI 大模型接入、Spring AI 核心特性、Prompt 工程和优化、RAG 检索增强、向量数据库、Tool Calling 工具调用、MCP 模型上下文协议、AI Agent 开发（Manas Java 实现）、Cursor AI 工具等核心知识。用一套教程将程序员必知必会的 AI 技术一
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- 编程导航 2025 年 AI 开发实战新项目，基于 Spring Boot 3 + Java 21 + Spring A
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx yu-ai-agentConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Yu AI Agent
Yu AI Agent is a comprehensive educational project and MCP server implementation built with Spring Boot 3 and Java 21, demonstrating how to build production-grade AI applications using Spring AI and LangChain4j. It includes two showcase applications: an AI relationship counselor app with multi-turn dialogue, RAG knowledge base retrieval, and tool calling; and YuManus, an autonomous ReAct-pattern agent that plans and executes complex tasks using web search, file operations, and PDF generation. The project covers the full spectrum of modern AI development — from LLM integration and vector databases to MCP protocol server development and serverless deployment.
Prerequisites
- Java 21 or higher (JDK 21+) installed
- Maven 3.8+ for building the project
- An AI API key from a supported provider (Alibaba Bailian / DashScope, OpenAI, or a local Ollama instance)
- PostgreSQL with PgVector extension for the RAG vector database
- Redis for session memory and rate limiting (optional for basic setup)
Clone the repository
Clone the yu-ai-agent project from GitHub to your local machine.
git clone https://github.com/liyupi/yu-ai-agent.git
cd yu-ai-agentConfigure your AI provider credentials
Copy the application configuration template and set your LLM API credentials. The project defaults to Alibaba Bailian (DashScope) but supports OpenAI and Ollama as well.
# Edit src/main/resources/application.yml
# Set your API key:
spring:
ai:
dashscope:
api-key: your_dashscope_api_key
# Or for OpenAI:
openai:
api-key: your_openai_api_keySet up the PostgreSQL vector database
Install and configure PostgreSQL with the pgvector extension for RAG knowledge base storage. Create the database and enable the extension.
# In PostgreSQL:
CREATE DATABASE yuai;
\c yuai
CREATE EXTENSION IF NOT EXISTS vector;Build and run the backend
Use Maven to build the project and start the Spring Boot application.
mvn clean install -DskipTests
mvn spring-boot:runConfigure the MCP server for external clients
The project exposes an MCP server for tool calling from external AI clients. Add the server configuration to your MCP client to connect to the running Spring Boot application.
{
"mcpServers": {
"yu-ai-agent": {
"command": "npx",
"args": ["yu-ai-agent"],
"env": {
"SERVER_URL": "http://localhost:8080"
}
}
}
}Load knowledge base documents for RAG
Use the provided API endpoints to upload documents to the RAG knowledge base. The system will embed them using PgVector for retrieval-augmented generation.
# Upload a document via the REST API:
curl -X POST http://localhost:8080/api/rag/upload \
-F '[email protected]'Yu AI Agent Examples
Client configuration
MCP client configuration connecting to the locally running Yu AI Agent Spring Boot server.
{
"mcpServers": {
"yu-ai-agent": {
"command": "npx",
"args": ["yu-ai-agent"]
}
}
}Prompts to try
Example prompts showcasing the AI agent's capabilities including RAG, tool calling, and autonomous planning.
- "Help me plan a romantic date in Beijing — search for nearby restaurants and attractions."
- "Based on my relationship knowledge base, what advice do you have for this situation?"
- "Use YuManus to research the best practices for Spring AI and generate a PDF report."
- "Search the web for today's AI news and summarize the top three stories."
- "What tools are available to you and what can you help me accomplish?"Troubleshooting Yu AI Agent
Spring Boot fails to start with 'pgvector extension not found' error
Ensure the pgvector extension is installed in your PostgreSQL instance. Run 'CREATE EXTENSION IF NOT EXISTS vector;' in the target database as a superuser. Verify PostgreSQL version is 14+ as older versions may not support pgvector.
LLM API calls fail with authentication errors
Check that your API key is correctly set in application.yml or passed as an environment variable (SPRING_AI_DASHSCOPE_API_KEY or SPRING_AI_OPENAI_API_KEY). Ensure the key is for the correct provider configured in the active Spring profile.
RAG retrieval returns irrelevant results
Ensure documents have been fully processed and embedded before querying — check the ingestion pipeline status via the API. Adjust the similarity threshold and top-K retrieval parameters in the application configuration for better precision.
Frequently Asked Questions about Yu AI Agent
What is Yu AI Agent?
Yu AI Agent is a Model Context Protocol (MCP) server that 编程导航 2025 年 ai 开发实战新项目，基于 spring boot 3 + java 21 + spring ai 构建 ai 恋爱大师应用和 react 模式自主规划智能体yumanus，覆盖 ai 大模型接入、spring ai 核心特性、prompt 工程和优化、rag 检索增强、向量数据库、tool calling 工具调用、mcp 模型上下文协议、ai agent 开发（manas java 实现）、cursor ai 工具等核心知识。用一套教程将程序员必知必会的 ai 技术一 It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Yu AI Agent?
Follow the installation instructions on the Yu AI Agent GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Yu AI Agent?
Yu AI Agent works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Yu AI Agent free to use?
Yes, Yu AI Agent is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Yu AI Agent Alternatives — Similar Coding Agents Servers
Looking for alternatives to Yu AI Agent? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Yu AI Agent in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Yu AI Agent?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.