agents-flex

agents-flex

Lightweight Java AI agent development framework supporting RAG, MCP, Skills, and more.

Agent SkillDevOpen sourceJavaAI 代理LLM 应用
Type
Agent Skill
Transport
http
Open source
Yes
GitHub Stars
★ 1.0k
Source
skill-github

Overview

Agents-flex is a lightweight Java AI agent development framework, positioned as an alternative to Spring AI. It supports various features such as RAG, MCP, Skills, Text2SQL, LLM Wiki, sub-agents, web search, TTS (synchronous and streaming), and STT. The framework aims to help enterprises and developers quickly build production-grade LLM applications. With Agents-flex, users can easily integrate mainstream LLM models and leverage built-in tool calling and data querying capabilities to enable zero-code data analysis and business logic encapsulation.

Capabilities

  • RAG support
  • MCP protocol integration
  • AI skill encapsulation
  • Text2SQL and natural language data analysis
  • Multi-format document loading
  • Vector store integration

Use cases

Enterprise-grade LLM application developmentCross-system context sharingTool orchestrationZero-code data querying

Setup

Requires: API KeyNode 环境
Add the dependency to your Maven project:\<dependency>\<groupId>com.agentsflex\</groupId>\<artifactId>agents-flex-core\</artifactId>\<version>2.1.8\</version>\</dependency>

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.

FAQ

How to configure the model?

Configure the model using the OpenAIChatConfig builder, supporting providers like GiteeAI and OpenAI.

Does it support asynchronous responses?

Yes, it supports synchronous, streaming, and asynchronous responses.

Related skills