#108 · Primary category: LLM Application Frameworks

agents-flex

agent ai chatbot chatgpt gpt langchain4j llama3 llm ollama spring-ai

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.

Project last updated:08/27/26

GitHub Stars

1.0K

Forks

143

Contributors

60

License

Apache-2.0

Why we included this project

Java teams that want LLM-powered services without adopting a heavyweight runtime will find a lot to work with here. The framework is modular: chat, embedding, image, audio, and rerank models sit behind unified interfaces, so you can move between OpenAI, Qwen, Ollama, or DeepSeek without touching your application code. Beyond plain chat, it bundles building blocks for RAG pipelines, tool calling, MCP clients, sub-agents, Text2SQL, and web search, plus an agent runtime that supports snapshot recovery and task planning. You pull in only the modules you need, whether you run plain Java 8, Spring Boot, or another JVM stack. Teams weighing it as a Spring AI alternative for production should look closely at its routing, retry, circuit-breaking, and OpenTelemetry observability support.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category