Solon Ai

What is Solon Ai?

Solon Ai is a Java AI application development framework that integrates LLMs, RAG (Retrieval-Augmented Generation), the MCP (Model Context Protocol), and Agent collaboration (ReAct, Team). It is a core subproject of the Solon project, designed to be a full-scenario framework comparable to LangChain, LangGraph, and LlamaIndex.

How to use Solon Ai?

Add the Solon Ai dependency from Maven Central (org.noear:solon-parent). Use core modules like ChatModel for unified LLM calls, RAG for knowledge base operations, MCP for tool/resource sharing, and Agent for graph-driven reasoning. Configuration can be done programmatically or via YAML (Ai Flow).

Key features of Solon Ai

• Multi-model dialect support (OpenAI, Gemini, Claude, Ollama, DeepSeek, Dashscope)
• Graph-driven agent orchestration with ReAct and Team collaboration
• Deep MCP protocol integration (both server and client)
• Full-link RAG pipeline (Loader, Splitter, Embedding, Reranking)
• Ai Flow low-code YAML orchestration for workflow automation
• Seamless integration with Solon, SpringBoot, Vert.X, and Quarkus ecosystems

Use cases of Solon Ai

• General-purpose autonomous agents (e.g., Manus, OpenOperator)
• Intelligent assistants & RAG knowledge bases (e.g., Dify, Coze)
• Multi-agent collaborative orchestration (e.g., AutoGPT, MetaGPT)
• Business-driven controlled workflows (e.g., AI-enhanced approval systems)
• Intelligent document processing & ETL (e.g., Instabase, Unstructured.io)

FAQ from Solon Ai

How does Solon Ai compare to LangChain or LlamaIndex?

Solon Ai is the same type of development framework as LangChain, LangGraph, and LlamaIndex, focusing on Java and the Solon ecosystem.

What runtime environments are supported?

Solon Ai supports JDK 8, 11, 17, 21, and 25.

Does Solon Ai support the MCP protocol?

Yes, it deeply integrates the MCP protocol (MCP_2025_06_18), enabling cross-platform tool, resource, and prompt sharing via annotations like @McpServerEndpoint and McpClientProvider.

Where can I find documentation and examples?

The official learning guide is at https://solon.noear.org/article/learn-solon-ai. Example projects are available on Gitee, GitCode, and GitHub (e.g., solon-ai-mcp-embedded-examples).

What LLM providers are compatible?

Solon Ai supports multiple providers via dialects: OpenAI, Gemini, Claude, Ollama, DeepSeek, Dashscope, and others through the ChatModel unified interface.