🛠️Spring AI Alibaba
alibaba/spring-ai-alibaba · homepage ↗
Agentic AI Framework for Java Developers
⭐ Very popular: 11k stars, gaining about 61 a week
View on GitHub ↗repo profile
momentum
durability
bus factor = how many people it takes to cover more than half the commits (6 months). 1 is a solo project; higher means the work is spread across a team. top-author share is the single busiest author's slice of those commits.
since we covered it
why it's a big deal
- Gives Java developers a native way to build agentic and multi-agent applications without leaving the Spring ecosystem, closing a gap that has mostly been filled by Python frameworks.
- Ships built-in orchestration patterns such as SequentialAgent, ParallelAgent, RoutingAgent, and LoopAgent, so teams do not have to hand-roll agent coordination logic.
- Targets production concerns directly with observability, evaluation, human-in-the-loop support, and context engineering features like context compaction and tool retry.
under the hood
- Builds on Spring AI and Spring Boot, using their ChatModel, tool calling, and message abstractions, and requires JDK 17 or later on a Maven project structure.
- Uses a graph core as the low-level runtime for stateful, long-running agents, supporting conditional routing, nested graphs, parallel execution, and PlantUML or Mermaid export.
- Integrates Nacos for Agent-to-Agent communication and dynamic configuration, supports the Model Context Protocol, and connects to LLM providers including DashScope, OpenAI, and DeepSeek.
Radar summary, generated from the project's public sources
star history
- PR#19 6k 2025-10-15
- now 11k + 4k since first covered
curve is sampled from GitHub's star history, plus our own daily readings since we covered it; the dashed stretch is before we first covered it, the solid line since. figures at coverage are the numbers we printed then (approx.), current count is live.
understory
Output and attention are roughly in balance.
- output, commits & releases
- clout, star velocity
output = commits & releases; clout = star velocity, both 0 to 100 monthly indices; the gap where output runs above clout is the understory. The understory →
covered in
-
Java framework to build agentic, multi-agent, workflow systems with MCPs
similar projects
compare these →- 🦌 DeerFlow
Python · 7.5× the stars
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
80k ACTIVE - 📖 ai-agent-book
Python · 3.6× the stars
AI Agent PDF
38k ACTIVE - 📚 Haystack
Python · 2.5× the stars
Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.
26k ACTIVE
comments
Sign in with GitHub to add your blip on Spring AI Alibaba.