Open-source long-horizon super agent harness that orchestrates sub-agents, memory, and sandboxes to research, code, and create across tasks lasting minutes to hours.
alibaba/spring-ai-alibaba
A Java framework for building agentic, workflow and multi-agent AI applications on top of Spring AI.
- Stars
- 11,044
- Forks
- 2,455
- Open issues
- 172
- Last commit
- 14 days ago
What is it?
Spring AI Alibaba is a Java framework for building AI agents, graph-based workflows and multi-agent systems. It extends Spring AI with an Agent Framework that provides built-in context engineering and human-in-the-loop support, along with workflow agents such as SequentialAgent, ParallelAgent, RoutingAgent and LoopAgent.
The underlying Graph runtime handles persistence, workflow orchestration and streaming for long-running stateful agents, and supports conditional routing, nested graphs and parallel execution. Workflows can be exported to PlantUML and Mermaid. The project also covers A2A agent-to-agent communication with Nacos integration, multimodal input, and a WebSocket-based voice agent.
The project includes Spring AI Alibaba Admin, a platform for visual agent development, observability, evaluation and MCP management, and requires JDK 17+. Its examples include a ChatBot that can be run with a DashScope API key.
Key features
- 01Multi-agent orchestration with Sequential, Parallel, Routing and Loop agents.
- 02Graph-based workflow runtime with conditional routing, nested graphs and state management.
- 03Built-in context engineering policies such as context compaction and tool retry.
- 04Support for multiple LLM providers including DashScope and OpenAI, plus MCP.
- 05A2A agent-to-agent communication integrated with Nacos.
- 06Export workflows to PlantUML and Mermaid formats.
Use cases
- Building Java backend services that embed LLM-driven agents with Spring Boot.
- Coordinating several specialized agents through routing or parallel workflows.
- Creating long-running stateful agents that need persistence and streaming.
- Prototyping and debugging agents visually with the Admin platform.
Quick start
- 1
Check prerequisites: JDK 17+ and an LLM provider API key
- 2
Clone the repository
git clone --depth=1 https://github.com/alibaba/spring-ai-alibaba.git - 3
Set the DashScope API key
export AI_DASHSCOPE_API_KEY=your-api-key - 4
Start the ChatBot example
./mvnw -pl examples/chatbot spring-boot:run
Things to know
- Requires JDK 17 or newer and a paid or account-based LLM API key, such as DashScope.
- The quick start example is configured for DashScope; other providers need extra setup from the docs.
Topics
FAQ
- What is spring-ai-alibaba?
- A Java framework for building agentic, workflow and multi-agent AI applications on top of Spring AI. Spring AI Alibaba is a Java framework for building AI agents, graph-based workflows and multi-agent systems. It extends Spring AI with an Agent Framework that provides built-in context engineering and human-in-the-loop support, along with workflow agents such as SequentialAgent, ParallelAgent, RoutingAgent and LoopAgent.
- Is spring-ai-alibaba free to use? What license does it have?
- spring-ai-alibaba is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
- Is spring-ai-alibaba still maintained?
- Actively maintained. The last commit to spring-ai-alibaba was on Oct 7, 2026.
- What can I use spring-ai-alibaba for?
- Building Java backend services that embed LLM-driven agents with Spring Boot. Coordinating several specialized agents through routing or parallel workflows. Creating long-running stateful agents that need persistence and streaming. Prototyping and debugging agents visually with the Admin platform.
- How do I install spring-ai-alibaba?
- Check prerequisites: JDK 17+ and an LLM provider API key Clone the repository: git clone --depth=1 https://github.com/alibaba/spring-ai-alibaba.git Set the DashScope API key: export AI_DASHSCOPE_API_KEY=your-api-key Start the ChatBot example: ./mvnw -pl examples/chatbot spring-boot:run
- Where can I get spring-ai-alibaba?
- The source code and installation instructions are on GitHub: https://github.com/alibaba/spring-ai-alibaba
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Open-source AI agent application platform built on Java, LangChain4j, Spring Boot and Vue 3, covering models, agents, RAG, Skills, MCP and text-to-SQL analysis.
A free, open-source Chinese-language book on AI Agent design principles and engineering practice, with 109 companion experiments and downloadable PDF/EPUB.
An opinionated, batteries-included agent harness for Python that runs long multi-step tasks out of the box on LangGraph.
FastGPT is an open-source AI Agent building platform with data processing, RAG knowledge bases, and visual workflow orchestration for LLM apps.
An SDK for building AI agents and multi-agent systems in Python, .NET and Java, with model, plugin and vector database integrations.