solon-ai

Java AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java26. It can also be embedded i

What is solon-ai?

Java AI application development framework (supports LLM-tool,skill; RAG; MCP; Agent-ReAct,Team-Agent). Compatible with java8 ~ java26. It can also be embedded in SpringBoot, jFinal, Vert.x, Quarkus, and other frameworks.

Overview of solon-ai

What it is

Solon AI is a core subproject of the Solon project. It is a full-scenario Java AI development framework that aims to deeply integrate LLM large models, RAG knowledge bases, MCP protocol, and Agent collaboration orchestration. It supports full use cases, fits perfectly into the Solon ecosystem, and can be seamlessly integrated into frameworks like SpringBoot, Vert.X, Quarkus, etc. It uses multi-model dialects to adapt model differences via ChatModel's unified interface and supports graph-driven orchestration for transforming Agent reasoning into observable computation flow graphs.

Key features

  • ChatModel: unified interface for synchronous and Reactive calls, built-in dialect adaptation, Tool, Skill, ChatSession support.
  • Talents: dynamic admission and instruction injection based on user context (e.g., VIP detection).
  • RAG: full-link support from DocumentLoader, DocumentSplitter, EmbeddingModel, to RerankingModel.
  • MCP: deep integration with MCP protocol (MCP_2025_06_18) for cross-platform tool, resource, and prompt sharing.
  • Agent: ReAct introspective reasoning and multi-agent Team collaboration with graph-driven flows.
  • Ai Flow: YAML-based process orchestration simulating low-code flow applications like Dify.

Use cases

  • 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 DingTalk/Lark approvals)
  • Intelligent Document Processing & ETL (e.g., Instabase, Unstructured.io)
  • Real-time Data Insights & Dashboards (e.g., Text-to-SQL applications)
  • Automated Testing & Quality Assurance (e.g., GitHub Copilot Workspace)
  • Low-Code/Visual AI Workflow Platforms (e.g., LangFlow, Flowise)

Getting started

See the repository README for installation and quick-start instructions.

License and pricing

Licensed under Apache-2.0. Open source.

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/opensolonsolon-ai.svg)](https://yunodb.com/tools/opensolonsolon-ai?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/opensolonsolon-ai?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/opensolonsolon-ai.svg" alt="Featured on YunoDB" height="20"></a>