Back to directory

Spring AI Alibaba

A production-ready Java framework for building agentic, workflow and multi-agent applications on top of Spring AI, with a graph runtime and a one-stop platform for agent development and management.

Spring AI Alibaba

Spring AI Alibaba is a production-ready framework for building agentic, workflow, and multi-agent applications in Java. Spring AI Alibaba Admin is a one-stop agent platform for visual agent development, observability, evaluation and MCP management, and can also migrate projects from the Dify low-code platform. The Agent Framework layer adds built-in context engineering and human-in-the-loop support, plus ready-made workflow patterns such as sequential, parallel, routing and loop agents.

Underneath, Spring AI Alibaba Graph provides the runtime: persistence, workflow orchestration and streaming for long-running, stateful agents, with a graph API for building more flexible multi-agent workflows, conditional routing, nested graphs, parallel execution and state management, and export to PlantUML and Mermaid. Other features include multimodal agents that understand images and can generate images or audio, a WebSocket-based real-time voice agent, and agent-to-agent communication built on Nacos for coordinating agents across services.

It supports multiple LLM providers, including DashScope and OpenAI, tool calling, and the Model Context Protocol, and is written in Java under the Apache-2.0 license.

More in Agent frameworks

See all 902
  • Recurse

    recurse.run

    A serverless harness that lets a coding agent design, test, and deploy its own specialist sub-agents as tools, MCP servers, or bots, defined by a schema-validated manifest.

  • ProofForge

    shulgin.is-a.dev

    An AI-agent pipeline that decomposes a mathematics problem, proves each piece, and formalizes the result in Lean 4 and Mathlib until the Lean kernel accepts it, with six of its proofs already merged into Google DeepMind's formal-conjectures repository.

  • local-coder

    github.com

    Builds a local coding-agent team on top of Ollama and OpenCode by detecting the machine's hardware, recommending models for seven specialist roles, and testing whether each assigned model can actually use tools, edit a repository and pass verification.