#5555th of 118 in Agent frameworks and SDKs
spring-ai
Spring-style Java API for chat models, embeddings, vector stores and tool calling
- Stars
- 9.6k
- License
- Apache-2.0
- Last commit
- Nov 2026
- Last release
- Oct 2026
- Language
- Java
8,422 on 21 Apr 20269,638 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Spring AI is a Java library that gives Spring Boot applications a portable API over model providers such as Anthropic, OpenAI, Amazon Bedrock, Google, Ollama, Mistral AI and DeepSeek. It covers chat, embedding, image, transcription, speech and moderation models, plus vector stores, tool calling, structured output to POJOs, chat memory, RAG and MCP starters. Version 2.x targets Spring Boot 4.x; 1.1.x targets Boot 3.5.x.
Who it is for: Java and Spring Boot developers adding LLM features to applications
Strengths
- Portable ChatClient API across many providers, with sync and streaming modes
- Boot starters and auto-configuration for models and vector stores
- About 20 vector stores behind one SQL-like metadata filter API
- MCP client and server starters with STDIO, SSE and Streamable-HTTP transports
Weaknesses
- Java and Spring Boot only; no support for other languages or frameworks
- 2.x requires Spring Boot 4; Boot 3.5 users must stay on 1.1.x
- A library, not a runnable app: no UI or hosted agent runtime
- Major-version split means upgrades need migration work per the upgrade notes
What it needs
- no GPU
- Needs Spring Boot, Maven, Model provider API or local runtime such as Ollama, Optional vector store
- Models: Anthropic, OpenAI, Amazon Bedrock, Google, Ollama
Quick answers
Is spring-ai open source?
Yes. Its code is on GitHub under the Apache-2.0 license.
Does spring-ai need a GPU?
No, it runs without one.
Also in Agent frameworks and SDKs
See all 118| Rank | Project | Score |
|---|---|---|
| 1 | ppt-masterAgent skill that turns documents into natively editable PowerPoint decks | 95 out of 100 |
| 2 | openai-agents-pythonPython SDK for multi-agent workflows with handoffs, guardrails and tracing | 91 out of 100 |
| 3 | mastraTypeScript framework for building AI agents, workflows and MCP servers | 91 out of 100 |
| #4 | browser-usePython library that lets an LLM agent control a web browser | 90 out of 100 |
| #5 | copilotkitSDK for adding agent chat, generative UI and shared state to apps | 90 out of 100 |