Spring AI
Spring / VMwareSpring's official AI framework. ChatClient, advisors, RAG, VectorStore, and full auto-configuration.
Async IO is the company behind Atmosphere — the real-time transport layer for Java AI agents. We provide the engineering, the support, and the long-term commitment that production systems require.
Build once with @Agent — deliver over any transport and any protocol.
Three distinct layers, each independently extensible.
Your application code declares what it does. Atmosphere handles how it is delivered — and falls back automatically when a transport is unavailable.
Add the dependency to your classpath and your agent speaks the protocol. No manual endpoint wiring, no boilerplate.
Atmosphere is the infrastructure layer underneath your LLM library. Your @Agent and @AiTool annotations work identically across all backends.
The Java AI ecosystem has seven frameworks. Each one is moving fast, each
one has its own release cadence, and each one could change direction
tomorrow. Atmosphere is the runtime-abstraction layer that
makes your @Agent, @AiEndpoint, and
@AiTool code portable across all seven — swap the
dependency, keep the code. Async IO maintains the abstraction and the
bridges; our support contract is the insurance policy against vendor
lock-in.
Spring's official AI framework. ChatClient, advisors, RAG, VectorStore, and full auto-configuration.
Java port of the LangChain ecosystem. Chains, AI services, streaming chat models, and tool bridging.
Agent Development Kit. Multi-agent orchestration, sessions, and the Runner execution engine.
Goal-driven agent framework from the creator of Spring. Declarative goals, planned execution, native PromptRunner.
Kotlin-native AI framework. Structured concurrency, typed tools, and a composable agent DSL.
Microsoft's enterprise-grade AI orchestration SDK. ChatCompletionService, kernel plugins, memory, planners.
Atmosphere's zero-dependency OpenAI-compatible client. Built for tests and local dev without pulling in a framework — works with OpenAI, Gemini, Ollama, and any compatible endpoint.
| Framework | Language | Vendor | Atmosphere bridge | Atmosphere support |
|---|---|---|---|---|
| Spring AI | Java | Spring / VMware | atmosphere-spring-ai | Included |
| LangChain4j | Java | Community | atmosphere-langchain4j | Included |
| Google ADK | Java | atmosphere-adk | Included | |
| Embabel | Kotlin | Embabel | atmosphere-embabel | Included |
| JetBrains Koog | Kotlin | JetBrains | atmosphere-koog | Included |
| Semantic Kernel | Java | Microsoft | atmosphere-semantic-kernel | Included |
| Built-in | Java | Async IO | atmosphere-ai | Included |
Atmosphere runs on top of each framework and its
ecosystem — Spring for Spring AI, the LangChain4j chain
library, Google ADK, Microsoft Semantic Kernel, JetBrains Koog, and
Embabel's planning engine. The Built-in runtime is
a zero-dependency OpenAI-compatible client for tests and local dev.
Whichever you pick, you code against one surface —
@Agent, @AiEndpoint, @AiTool
— and you get more than any framework ships on its own.
Every framework provides these. Atmosphere normalizes them behind one annotation surface, so your agent code is identical whether you run on Spring AI, Koog, or anything in between.
The wider JVM ecosystem has pieces of some of these —
Spring has WebSocket and Kafka, Spring Integration has channel
adapters, there are community MCP clients. Atmosphere is what
wires every item below directly to your
@Agent / @AiTool code, shipped as one
coherent stack and covered by one SLA — instead of half a
dozen separate libraries your team glues together.
You are not shopping between Spring AI and LangChain4j — you already want an agent stack that does not lock you into one framework, one LLM provider, or one vendor. Atmosphere is that stack. Async IO has been selling the support contract that covers the abstraction and the swap — every year, since 2014.
Everything you need to build, deploy, and operate AI agents in production. Spring Boot 4.0 and Quarkus 3.21+ auto-configuration included.
One class, one annotation. Endpoints, commands, tools, skill files, conversation memory, and protocol exposure are all auto-wired.
Manage fleets of agents with parallel fan-out, sequential pipelines, conditional routing, and result evaluation.
CheckpointStore persists workflow state as parent-chained snapshots. Pause workflows without holding a thread; resume via REST.
@RequiresApproval pauses tool execution for human approval. The virtual thread parks cheaply until the client responds.
Web, Slack, Telegram, Discord, WhatsApp, Messenger. Set a bot token and the same @Command + AI pipeline works everywhere.
Real-time dashboard, 25 REST endpoints, WebSocket event stream, and MCP tools for managing agents and runtimes.
OpenTelemetry tracing, Micrometer metrics, and AI token usage tracking. Auto-configured with Spring Boot.
atmosphere.js with React, Vue, Svelte, and React Native hooks. Streaming, offline queues, auth token refresh.
Atmosphere has been in continuous production since 2008 — powering trading floors, healthcare systems, collaboration tools, and AI applications at companies from startups to the Fortune 500. The team brings over 30 years of experience in real-time systems, JVM internals, and AI infrastructure.
We contributed to Java NIO/AIO and have been shipping real-time Java infrastructure since before WebSocket was standardized. Atmosphere itself has been open source since day one, and the project is backed by a team of Java Champions and Apache Committers who have been active in the JVM ecosystem for decades.
Get direct access to the core engineering team. We wrote the framework, we maintain it, and we stand behind it. Meet your production schedule and compliance requirements with guaranteed response times.
Still running Atmosphere 2.x or 3.x in production? We provide long-term support, security patches, and migration guidance for legacy deployments. Includes a migration path to Atmosphere 4.x when you are ready.