LnYo-Cly/ai4j

Java 8+ agentic SDK: unified LLM access (OpenAI/Anthropic/DashScope/Doubao/DeepSeek...), Tool Calling, MCP, RAG, Agent Runtime, and a built-in Coding Agent CLI/TUI/ACP.

What it solves

It provides a unified Java-based development kit for building AI agents, eliminating the need to write platform-specific code when switching between different large language model (LLM) providers.

How it works

The SDK offers a standardized interface for model access, tool calling, and agent runtimes. It abstracts the complexities of various AI platforms (such as OpenAI, Anthropic, and DeepSeek) into a consistent API, allowing developers to change providers by simply updating the configuration and platform type.

Who it’s for

Java developers using JDK 8 or newer who want to integrate LLMs, RAG, and agentic workflows into their applications without being locked into a single AI vendor.

Highlights

  • Broad Platform Support: Compatible with OpenAI, Anthropic, DeepSeek, Ollama, and many others.
  • Agentic Capabilities: Built-in support for Tool Calling, Model Context Protocol (MCP), and Agent-to-Agent (A2A) communication.
  • Integrated RAG: Includes built-in Retrieval-Augmented Generation support and integration with vector stores like Pinecone, Milvus, and Redis.
  • Developer Tools: Comes with a built-in Coding Agent available via CLI, TUI, and ACP.

Related

  • Project
    a2aproject/a2a-java

    A Java SDK that implements the Agent2Agent (A2A) Protocol, enabling Java-based AI agents to communicate via JSON-RPC, gRPC, and REST.

  • Project
    opensolon/solon-ai

    A full-scenario Java AI development framework for building LLM applications, RAG knowledge bases, and multi-agent systems with native integration into the Java ecosystem.

  • Project
    agents-flex/agents-flex

    A lightweight, modular AI application framework for Java that provides unified abstractions for LLMs, RAG, and agents, with production-ready tooling for Spring Boot integration.

  • Project
    codeany-ai/open-agent-sdk-typescript

    An open-source TypeScript SDK for running autonomous AI agents in-process, featuring a vast library of built-in tools and support for multiple LLM providers.

  • Project
    mozilla-ai/any-agent

    A unified interface and evaluation tool that allows developers to run and compare AI agents across multiple frameworks like LangChain, LlamaIndex, and OpenAI Agents SDK using a single API.