[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-4135":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":23,"hasPages":23,"topics":25,"createdAt":10,"pushedAt":10,"updatedAt":35,"readmeContent":36,"aiSummary":37,"trendingCount":16,"starSnapshotCount":16,"syncStatus":38,"lastSyncTime":39,"discoverSource":40},4135,"spring-ai-alibaba","alibaba\u002Fspring-ai-alibaba","alibaba","Agentic AI Framework for Java Developers","https:\u002F\u002Fjava2ai.com",null,"Java",9975,2221,108,208,0,11,84,419,71,116,"Apache License 2.0",false,"main",[26,27,28,29,30,31,32,33,34],"agentic","artificial-intelligence","context-engineering","graph","java","multi-agent","reactagent","spring-ai","workflow","2026-06-12 04:00:21","# [Spring AI Alibaba](https:\u002F\u002Fjava2ai.com)\n\n[![License](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Flicense-Apache%202-4EB1BA.svg)](https:\u002F\u002Fwww.apache.org\u002Flicenses\u002FLICENSE-2.0.html)\n[![CI Status](https:\u002F\u002Fgithub.com\u002Falibaba\u002Fspring-ai-alibaba\u002Fworkflows\u002F%F0%9F%9B%A0%EF%B8%8F%20Build%20and%20Test\u002Fbadge.svg)](https:\u002F\u002Fgithub.com\u002Falibaba\u002Fspring-ai-alibaba\u002Factions?query=workflow%3A%22%F0%9F%9B%A0%EF%B8%8F+Build+and+Test%22)\n[![Ask DeepWiki](https:\u002F\u002Fdeepwiki.com\u002Fbadge.svg)](https:\u002F\u002Fdeepwiki.com\u002Falibaba\u002Fspring-ai-alibaba)\n[![Maven central](https:\u002F\u002Fimg.shields.io\u002Fmaven-central\u002Fv\u002Fcom.alibaba.cloud.ai\u002Fspring-ai-alibaba.svg)](https:\u002F\u002Fimg.shields.io\u002Fmaven-central\u002Fv\u002Fcom.alibaba.cloud.ai\u002Fspring-ai-alibaba)\n\u003Cimg alt=\"gitleaks badge\" src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fprotected%20by-gitleaks-blue\">\n\n\u003Chtml>\n    \u003Ch3 align=\"center\">\n      A production-ready framework for building Agentic, Workflow, and Multi-agent applications.\n    \u003C\u002Fh3>\n    \u003Ch3 align=\"center\">\n      \u003Ca href=\"https:\u002F\u002Fjava2ai.com\u002Fdocs\u002Fquick-start\u002F\" target=\"_blank\">Agent Framework Docs\u003C\u002Fa>,\n      \u003Ca href=\"https:\u002F\u002Fjava2ai.com\u002Fdocs\u002Fframeworks\u002Fgraph-core\u002Fquick-start\u002F\" target=\"_blank\">Graph Docs\u003C\u002Fa>,\n      \u003Ca href=\"https:\u002F\u002Fjava2ai.com\u002Fecosystem\u002Fspring-ai\u002Freference\u002Fconcepts\u002F\" target=\"_blank\">Spring AI\u003C\u002Fa>,\n      \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Falibaba\u002Fspring-ai-alibaba\u002Ftree\u002Fmain\u002Fexamples\" target=\"_blank\">Examples\u003C\u002Fa>.\n    \u003C\u002Fh3>\n\u003C\u002Fhtml>\n\n## Architecture\n\n\u003Cp align=\"center\">\n    \u003Cimg src=\".\u002Fdocs\u002Fimgs\u002Farchitecture-new.png\" alt=\"architecture\" style=\"max-width: 740px; height: auto\" \u002F>\n\u003C\u002Fp>\n\n**Spring AI Alibaba Admin** is a one-stop Agent platform that supports visualized Agent development, observability, evaluation, and MCP management, etc. It also integrates with open-source low-code platforms like Dify, enabling rapid migration from DSL to Spring AI Alibaba project.\n\n**Spring AI Alibaba Agent Framework** is an agent development framework that can quickly develop agents with built-in **Context Engineering** and **Human In The Loop** support. For scenarios requiring more complex process control, Agent Framework offers built-in workflows like `SequentialAgent`, `ParallelAgent`, `RoutingAgent`, `LoopAgent`.\n\n**Spring AI Alibaba Graph** serves as the underlying runtime of the Agent Framework, providing essential capabilities such as persistence, workflow orchestration, and streaming required for long-running stateful agents. Compared to the Agent Framework, users can build more flexible multi-agent workflows based on the Graph API.\n\n## Core Features\n\n* **[Multi-Agent Orchestration](https:\u002F\u002Fgithub.com\u002Falibaba\u002Fspring-ai-alibaba\u002Ftree\u002Fmain\u002Fexamples\u002Fmultiagent-patterns)**: Compose multiple agents with built-in patterns including `SequentialAgent`, `ParallelAgent`, `RoutingAgent`, and `LoopAgent` for complex task execution.\n\n* **[Multimodal Support](https:\u002F\u002Fgithub.com\u002Falibaba\u002Fspring-ai-alibaba\u002Ftree\u002Fmain\u002Fexamples\u002Fmultimodal)**: ReactAgent with text and media input (image understanding). ReactAgent with tool based image or audio generation.\n\n* **[Voice Agent](https:\u002F\u002Fgithub.com\u002Falibaba\u002Fspring-ai-alibaba\u002Ftree\u002Fmain\u002Fexamples\u002Fvoice-agent)**: WebSocket-based real-time voice agent that supports streaming audio or text input and responds with generated audio.\n\n* **[Context Engineering](https:\u002F\u002Fjava2ai.com\u002Fdocs\u002Fframeworks\u002Fagent-framework\u002Ftutorials\u002Fhooks)**: Built-in best practices for context engineering policies to improve agent reliability and performance, including human-in-the-loop, context compaction, context editing, model & tool call limit, tool retry, planning, dynamic tool selection.\n\n* **[Graph-based Workflow](https:\u002F\u002Fjava2ai.com\u002Fdocs\u002Fframeworks\u002Fgraph-core\u002Fquick-start)**: Graph based workflow runtime and api for conditional routing, nested graphs, parallel execution, and state management. Export workflows to PlantUML and Mermaid formats.\n\n* **[A2A Support](https:\u002F\u002Fjava2ai.com\u002Fdocs\u002Fframeworks\u002Fagent-framework\u002Fadvanced\u002Fa2a)**: Agent-to-Agent communication support with Nacos integration, enabling distributed agent coordination and collaboration across services.\n\n* **[Rich Model, Tool and MCP Support](https:\u002F\u002Fjava2ai.com\u002Fintegration\u002Fchatmodels\u002FdashScope)**: Leveraging core concepts of Spring AI, supports multiple LLM providers (DashScope, OpenAI, etc.), tool calling, and Model Context Protocol (MCP).\n\n* **[One-stop Agent Platform](https:\u002F\u002Fjava2ai.com\u002Fecosystem\u002Fadmin\u002Fquick-start)**: Build agent in a visualized way, deploy agent without code or export as a standalone java project.\n\n\u003Cp align=\"center\">\n    \u003Cimg src=\".\u002Fdocs\u002Fimgs\u002Fsaa-admin.png\" alt=\"architecture\" style=\"max-width: 740px; height: auto\" \u002F>\n\u003C\u002Fp>\n\n## Getting Started\n\n### Prerequisites\n\n* Requires JDK 17+.\n* Choose your LLM provider and get the API-KEY.\n\n### Quickly Run a ChatBot\n\nThere's a ChatBot example provided by the community at [examples\u002Fchatbot](https:\u002F\u002Fgithub.com\u002Falibaba\u002Fspring-ai-alibaba\u002Ftree\u002Fmain\u002Fexamples\u002Fchatbot).\n\n1. Download the code.\n\n\t```shell\n\tgit clone --depth=1 https:\u002F\u002Fgithub.com\u002Falibaba\u002Fspring-ai-alibaba.git\n\tcd spring-ai-alibaba\n\t```\n\n2. Start the ChatBot.\n\n\tBefore starting, set API-KEY first (visit \u003Ca href=\"https:\u002F\u002Fbailian.console.aliyun.com\u002F?apiKey=1&tab=api#\u002Fapi\" target=\"_blank\">Aliyun Bailian\u003C\u002Fa> to get API-KEY):\n\t```shell\n\t# this example uses 'spring-ai-alibaba-starter-dashscope', visit https:\u002F\u002Fjava2ai.com to learn how to use OpenAI\u002FDeepSeek.\n\texport AI_DASHSCOPE_API_KEY=your-api-key\n\t```\n\t\n\t```shell\n\t# Maven installation is optional when using mvnw.\n\t.\u002Fmvnw -pl examples\u002Fchatbot spring-boot:run\n\t```\n\n3. Chat with ChatBot.\n\n\tOpen the browser and visit [http:\u002F\u002Flocalhost:8080\u002Fchatui\u002Findex.html](http:\u002F\u002Flocalhost:8080\u002Fchatui\u002Findex.html) to chat with the ChatBot.\n\t\n\u003Cp align=\"center\">\n\t\u003Cimg src=\".\u002Fdocs\u002Fimgs\u002Fchatbot-chat-ui.gif\" alt=\"chatbot-ui\" style=\"max-width: 740px; height: auto\" \u002F>\n\u003C\u002Fp>\n\n## Chatbot Code Explained\n\n1. Add dependencies\n\n\t```xml\n\t\u003Cdependencies>\n\t  \u003Cdependency>\n\t    \u003CgroupId>com.alibaba.cloud.ai\u003C\u002FgroupId>\n\t    \u003CartifactId>spring-ai-alibaba-agent-framework\u003C\u002FartifactId>\n\t    \u003Cversion>1.1.2.0\u003C\u002Fversion>\n\t  \u003C\u002Fdependency>\n\t  \u003C!-- Assume you are going to use DashScope Model. Refer to docs for how to choose model.-->\n\t  \u003Cdependency>\n\t    \u003CgroupId>com.alibaba.cloud.ai\u003C\u002FgroupId>\n\t    \u003CartifactId>spring-ai-alibaba-starter-dashscope\u003C\u002FartifactId>\n\t    \u003Cversion>1.1.2.1\u003C\u002Fversion>\n\t  \u003C\u002Fdependency>\n\t\u003C\u002Fdependencies>\n\t```\n\n2. Define Chatbot\n   \n\tFor more details of how to write a Chatbot, please check the [Quick Start](https:\u002F\u002Fjava2ai.com\u002Fdocs\u002Fquick-start) on our official website.\n\n## 📚 Documentation\n* [Overview](https:\u002F\u002Fjava2ai.com\u002Fdocs\u002Foverview) - High level overview of the framework\n* [Quick Start](https:\u002F\u002Fjava2ai.com\u002Fdocs\u002Fquick-start) - Get started with a simple agent\n* [Agent Framework Tutorials](https:\u002F\u002Fjava2ai.com\u002Fdocs\u002Fframeworks\u002Fagent-framework\u002Ftutorials\u002Fagents) - Step by step tutorials\n* [Use Graph API to Build Complex Workflows](https:\u002F\u002Fjava2ai.com\u002Fdocs\u002Fframeworks\u002Fagent-framework\u002Fadvanced\u002Fcontext-engineering) - In-depth user guide for building multi-agent and workflows\n* [Spring AI Basics](https:\u002F\u002Fjava2ai.com\u002Fecosystem\u002Fspring-ai\u002Freference\u002Fconcepts) - Ai Application basic concepts, including ChatModel, MCP, Tool, Messages, etc.\n* [Chat Memory](https:\u002F\u002Fdocs.spring.io\u002Fspring-ai\u002Freference\u002Fapi\u002Fchatclient.html#chat-memory) - Spring AI reference for chat memory repositories and usage\n\n## Project Structure\n\nThis project consists of several core components:\n\n* spring-ai-alibaba-agent-framework: A multi-agent framework designed for building intelligent agents with built-in context engineering best practices.\n* spring-ai-alibaba-graph: The underlying runtime for Agent Framework. We recommend developers to use Agent Framework but it's totally fine to use the Graph API directly.\n* spring-ai-alibaba-admin: A one-stop Agent platform that supports visualized Agent development, observability, evaluation, and MCP management, etc.\n* spring-ai-alibaba-studio: The embedded ui for quickly debugging agent in a visualized way.\n* spring-boot-starters: Starters integrating Agent Framework with Nacos to provide A2A and dynamic config features.\n\n## Spring AI Alibaba Ecosystem\n Repository | Description | ⭐\n  --- | --- | ---\n| [Spring AI Alibaba Graph](https:\u002F\u002Fgithub.com\u002Falibaba\u002Fspring-ai-alibaba\u002Ftree\u002Fmain\u002Fspring-ai-alibaba-graph-core) | A low-level orchestration framework and runtime for building, managing, and deploying long-running, stateful agents. | ![GitHub Repo stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Falibaba\u002Fspring-ai-alibaba?style=for-the-badge&label=)\n| [Spring AI Alibaba Admin](https:\u002F\u002Fgithub.com\u002Fspring-ai-alibaba\u002Fspring-ai-alibaba-admin) |  Local visualization toolkit for the development of agent applications, supporting project management, runtime visualization, tracing, and agent evaluation. | ![GitHub Repo stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fspring-ai-alibaba\u002Fspring-ai-alibaba-admin?style=for-the-badge&label=)\n| [Spring AI Extensions](https:\u002F\u002Fgithub.com\u002Fspring-ai-alibaba\u002Fspring-ai-extensions) | Extended implementations for Spring AI core concepts, including DashScopeChatModel, MCP registry, etc. |  ![GitHub Repo stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fspring-ai-alibaba\u002Fspring-ai-extensions?style=for-the-badge&label=)\n| [Spring AI Alibaba Examples](https:\u002F\u002Fgithub.com\u002Fspring-ai-alibaba\u002Fexamples) | Spring AI Alibaba Examples. |  ![GitHub Repo stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fspring-ai-alibaba\u002Fexamples?style=for-the-badge&label=)\n| [JManus](https:\u002F\u002Fgithub.com\u002Fspring-ai-alibaba\u002Fjmanus) | A Java implementation of Manus built with Spring AI Alibaba, currently used in many applications within Alibaba Group. | ![GitHub Repo stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fspring-ai-alibaba\u002Fjmanus?style=for-the-badge&label=)\n| [DataAgent](https:\u002F\u002Fgithub.com\u002Fspring-ai-alibaba\u002Fdataagent) | A natural language to SQL project based on Spring AI Alibaba, enabling you to query databases directly with natural language without writing complex SQL. | ![GitHub Repo stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fspring-ai-alibaba\u002Fdataagent?style=for-the-badge&label=)\n| [DeepResearch](https:\u002F\u002Fgithub.com\u002Fspring-ai-alibaba\u002Fdeepresearch) |  Deep Research implemented based on spring-ai-alibaba-graph. | ![GitHub Repo stars](https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Fstars\u002Fspring-ai-alibaba\u002Fdeepresearch?style=for-the-badge&label=)\n\n## Contact Us\n\n* Dingtalk Group (钉钉群), search `94405033092` and join.\n\n\u003Cimg src=\".\u002Fdocs\u002Fimgs\u002Fdingding-group.png\" style=\"width: 260px; height: auto\"\u002F>\n\n* WeChat Group (微信公众号), scan the QR code below and follow us.\n\n\u003Cimg src=\".\u002Fdocs\u002Fimgs\u002Fwechat-account.jpg\" style=\"width: 260px; height: auto\"\u002F>\n\n## Resources\n* [AI-Native Application Architecture White Paper](https:\u002F\u002Fdeveloper.aliyun.com\u002Febook\u002F8479)：Co-authored by 40 frontline engineers and endorsed by 15 industry experts, this 200,000+ word white paper is the first comprehensive guide dedicated to the full DevOps lifecycle of AI-native applications. It systematically breaks down core concepts and key challenges, offering practical problem-solving approaches and architectural insights.\n\n\n## Star History\n\n[![Star History Chart](https:\u002F\u002Fstarchart.cc\u002Falibaba\u002Fspring-ai-alibaba.svg?variant=adaptive)](https:\u002F\u002Fstarchart.cc\u002Falibaba\u002Fspring-ai-alibaba)\n\n---\n\n\u003Cp align=\"center\">\n    Made with ❤️ by the Spring AI Alibaba Team\n","Spring AI Alibaba 是一个面向Java开发者的智能代理框架，用于构建多代理、工作流和复杂的人工智能应用程序。其核心功能包括多代理编排、上下文工程支持以及人机协作机制，并提供了如顺序执行、并行处理、路由选择及循环控制等多种内置工作流模式以应对复杂的任务需求。此外，该项目还支持多媒体输入输出处理，增强了应用的交互性和实用性。适用于需要实现智能化决策流程的企业级应用场景，特别是在自动化服务、智能客服系统等领域有着广泛的应用前景。",2,"2026-06-11 02:58:38","top_language"]