agents-flex
Agents-flex is A lightweight Java AI agent development framework (positioned as a counterpart to Spring AI). It supports features such as RAG, MCP, Skills, Text
What is agents-flex?
Agents-flex is A lightweight Java AI agent development framework (positioned as a counterpart to Spring AI). It supports features such as RAG, MCP, Skills, Text2SQL , LLM Wiki, Sub-agents, Web Search, TTS (synchronous and streaming), and STT.
Overview of agents-flex
What it is
agents-flex is a lightweight Java AI agent development framework. It organizes LLM calls, Tool Calling, Agents, RAG, vector stores, Embedding, image generation, audio, MCP, Skills, Text2SQL, and related capabilities into clear modules. It is positioned as a counterpart to Spring AI. The framework requires JDK 8+ for most modules, with the MCP module requiring JDK 17+. The current repository version is 2.3.0.
Key features
- Java native: Core modules are compatible with Java 8+ and can run in plain Java, Spring Boot, or other JVM stacks.
- Unified model abstractions:
ChatModel,EmbeddingModel,ImageModel,RerankModel, and other interfaces wrap provider-specific capabilities. - Consistent sync and streaming APIs: The same Prompt, Options, interceptor, and context mechanisms work for both normal chat and streaming output.
- Complete Tool Calling flow: Supports annotation-based scanning, programmatic tool building, tool execution, tool message feedback, and tool-level observability.
- Durable Agent runtime: Provides snapshot recovery, tool approval, version-safe persistence, middleware, and event streams.
- Full RAG building blocks: Includes document models, parsing, splitting, Embedding, vector stores, retrieval, and Rerank support.
- Production-oriented design: Includes model routing, retry, load balancing, circuit breaking, OpenTelemetry observability, and Text2SQL safety interceptors.
Use cases
Building intelligent customer service, enterprise knowledge bases, natural-language data analysis, Agent workflows, model gateways, AI-assisted office tools, plugin-based tool systems, and Java services that need to connect to multiple model providers at the same time.
Getting started
For plain Java projects, use the aggregate dependency: xml com.agentsflex agents-flex-bom 2.3.0 pom import For Spring Boot projects, use the starter: xml com.agentsflex agents-flex-spring-boot-starter 2.3.0 You can also depend on only the modules you need. The quick start example uses an OpenAI-compatible API. Replace endpoint, model, and apiKey with your own model service configuration. See the repository README for a complete example.
License and pricing
The license is Apache-2.0. The pricing type is open source.
Based on the project's public README and repository metadata.
