Spring AI integrations and ecosystem extensions for Java applications.
MCP · Vector stores · Chat memory · RAG · Observability
Documentation · Quick Start · ARGI · 简体中文
ARGI stands for Agent Runtime and Graph Intelligence and is pronounced "AR-jee" (/ˈɑːr.dʒiː/). ARGI Extensions provides Spring AI integrations for MCP, vector stores, chat memory, RAG, prompt management, and observability. Use these modules directly with Spring AI or combine them with the ARGI framework.
- MCP: registry, router, distributed service, and gateway modules.
- Data and memory: vector stores and chat memory repositories for common databases and cloud services.
- RAG: reusable retrieval-augmented generation components.
- Operations: Nacos prompt management and ARMS observation integration.
Requirements: JDK 17 or later and Maven 3.9.1 or later. Install the local development modules with Maven:
git clone --depth=1 https://github.com/agentic-ai-java/argi-extensions.git
cd argi-extensions
mvn -DskipTests installImport the Extensions BOM and add the starters you need to your project:
<dependencyManagement>
<dependencies>
<dependency>
<groupId>io.github.agentic-ai-java</groupId>
<artifactId>argi-extensions-bom</artifactId>
<version>2.1.0-RC1</version>
<type>pom</type>
<scope>import</scope>
</dependency>
</dependencies>
</dependencyManagement>
<dependencies>
<dependency>
<groupId>io.github.agentic-ai-java</groupId>
<artifactId>argi-starter-mcp-registry</artifactId>
</dependency>
</dependencies>Issues and pull requests are welcome. Report problems and suggestions through GitHub Issues.
ARGI Extensions is available under the Apache License 2.0.
