Atmosphere

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.

Talk to Us Support Plans
5 Transports WebSocket, SSE, WebTransport/HTTP3, Long-Polling, gRPC
3 Agent Protocols MCP, A2A, AG-UI
9 AI Runtimes Built-in, Spring AI, LangChain4j, ADK, Koog, Semantic Kernel, AgentScope, Embabel, Spring AI Alibaba
18 Years in production
The Platform

Transports. Protocols. Runtimes.

Build once with @Agent — deliver over any transport and any protocol. Three distinct layers, each independently extensible.

Transports

5 transports, one API

Your application code declares what it does. Atmosphere handles how it is delivered — and falls back automatically when a transport is unavailable.

  • WebSocket Full-duplex communication over a single TCP connection.
  • SSE Server-Sent Events.
  • WebTransport/HTTP3 Multiplexed, low-latency transport over QUIC.
  • Long-Polling HTTP long-polling with automatic reconnection.
  • gRPC High-performance RPC framework with bidirectional streaming over HTTP/2.
Auto-fallbackReconnection with jitterHeartbeatsMessage caching
Agent Protocols

3 protocols, zero configuration

Add the dependency to your classpath and your agent speaks the protocol. No manual endpoint wiring, no boilerplate.

  • MCP Model Context Protocol.
  • A2A Agent-to-Agent protocol by Google.
  • AG-UI Agent-User Interaction protocol.
Auto-registered from classpathMulti-channel: Slack, Telegram, Discord, WhatsApp, Messenger
AI Runtimes

9 backends, swap by dependency

Atmosphere is the infrastructure layer underneath your LLM library. Your @Agent and @AiTool annotations work across every backend; capability flags are pinned by AbstractAgentRuntimeContractTest so adapter rows cannot drift from the running code.

  • Built-in Atmosphere's zero-dependency OpenAI-compatible client.
  • Spring AI Spring's official AI framework.
  • LangChain4j Java port of the LangChain ecosystem.
  • Google ADK Google's Agent Development Kit.
  • JetBrains Koog Kotlin-native AI framework by JetBrains.
  • Semantic Kernel Microsoft's enterprise-grade AI orchestration SDK.
  • Alibaba AgentScope Alibaba's multi-agent framework.
  • Embabel Goal-driven agent framework by Rod Johnson, the creator of Spring.
  • Spring AI Alibaba Spring AI Alibaba ReactAgent.
Portable @AiTool across all backendsCapability matrix CI-pinnedNo code change to swap runtime
Framework Support

One support contract. Every Java AI framework.

The Java AI ecosystem has eight third-party agent 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 of them — nine total runtimes counting Atmosphere's own Built-in OpenAI-compatible client. 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 AI

Spring / VMware

Spring's official AI framework. ChatClient, advisors, RAG, VectorStore, and full auto-configuration.

atmosphere-spring-ai Bridged

LangChain4j

Community

Java port of the LangChain ecosystem. Chains, AI services, streaming chat models, and tool bridging.

atmosphere-langchain4j Bridged

Google ADK

Google

Agent Development Kit. Multi-agent orchestration, sessions, and the Runner execution engine.

atmosphere-adk Bridged

JetBrains Koog

JetBrains

Kotlin-native AI framework. Structured concurrency, typed tools, multi-agent orchestration, Bedrock cache control.

atmosphere-koog Bridged

Semantic Kernel

Microsoft

Microsoft's enterprise-grade AI orchestration SDK. ChatCompletionService, kernel plugins, memory, planners.

atmosphere-semantic-kernel Bridged

Alibaba AgentScope

Alibaba

Multi-agent framework from Alibaba. Structured output, conversation memory, and token usage on top of explicit tool dispatch managed in your code.

atmosphere-agentscope Bridged

Embabel

Embabel

Goal-driven agent framework from the creator of Spring. Declarative goals, planned execution, native PromptRunner.

atmosphere-embabel Bridged

Spring AI Alibaba

Alibaba

Spring AI Alibaba ReactAgent. Structured output and conversation memory through the Spring AI ChatClient surface.

atmosphere-spring-ai-alibaba Bridged

Built-in

Async IO

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.

atmosphere-ai Bridged
At-a-glance: nine runtimes, one bridge layer, one support contract.
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 Google atmosphere-adk Included
JetBrains Koog Kotlin JetBrains atmosphere-koog Included
Semantic Kernel Java Microsoft atmosphere-semantic-kernel Included
Alibaba AgentScope Java Alibaba atmosphere-agentscope Included
Embabel Kotlin Embabel atmosphere-embabel Included
Spring AI Alibaba Java Alibaba atmosphere-spring-ai-alibaba Included
Built-in Java Async IO atmosphere-ai Included

Abstracted, portable, and then some

Atmosphere runs on top of each framework and its ecosystem — Spring AI, LangChain4j, Google ADK, Microsoft Semantic Kernel, JetBrains Koog, Alibaba AgentScope, Embabel's planning engine, and Spring AI Alibaba's ReactAgent. 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.

Abstracted through the @Agent API

Portable across all 9 runtimes

Every framework provides these. Atmosphere normalizes them behind one annotation surface, so your agent code is identical whether you run on Spring AI, Koog, AgentScope, or anything in between — and the capability matrix is CI-pinned so the adapter rows can't drift from the running code.

  • Streaming text to any client
  • Tool calling with @AiTool and JSON-schema parameters
  • Human-in-the-loop approval gates via @RequiresApproval
  • Structured output with response schemas
  • Conversation memory across turns
  • Vision and multi-modal input on any framework that supports it
  • Token-usage accounting on every response
  • Per-request retry policy and prompt caching
Only with Atmosphere

Wired to your agent, not to your infra team

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.

  • Cross-framework @Agent portability — one codebase, nine runtimes
  • Real-time streaming transport: WebSocket, SSE, WebTransport/HTTP3, gRPC, long-poll with automatic fallback
  • @Coordinator + @Fleet multi-agent orchestration over A2A v1.0.0 (released spec)
  • Durable HITL workflows — agent state survives JVM restart via CheckpointStore
  • @Command routing to Slack, Telegram, Discord, WhatsApp, Messenger
  • Rooms, presence, and broadcaster clustering over Kafka or Redis
  • MCP server — expose @AiTool to Claude, Copilot, Cursor, any MCP client
  • atmosphere.js client SDK with React, Vue, Svelte, and React Native hooks
  • Compliance evidence pinned in CI — OWASP Agentic Top 10, EU AI Act, HIPAA, SOC 2
  • Plan-and-verify — refuse unsafe LLM-emitted workflows before any tool fires
  • MS Agent Governance Toolkit YAML interop — same schema, same audit_entry shape
  • Enterprise support since 2014

No vendor lock-in. One support contract.

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 since 2014.

Without Atmosphere

Locked in

  • One framework, chosen up front.
  • One LLM provider, locked into its pricing and SLA.
  • Rewrite the agent when the framework changes direction, goes EOL, or gets acquired.
  • Separate support contracts with each vendor. No one owns the integration.
  • No escape hatch if the bet goes wrong.
With Atmosphere + Async IO support

Portable, covered

  • Nine runtimes — Built-in plus eight framework adapters. Swap the dependency when the winner changes.
  • Any LLM provider supported by any of the nine runtimes. Move when pricing shifts, rate limits bite, or a new model lands.
  • The abstraction holds. Your @Agent, @AiEndpoint, and @AiTool code do not move.
  • One support contract with Async IO. We have been shipping Atmosphere and writing every bridge on this page since 2014.
  • The escape hatch is the product. The swap is what you are paying us to maintain.
Talk to Us Support Tiers
What We Deliver

Production-grade agent infrastructure

Everything you need to build, deploy, and operate AI agents in production. Spring Boot 4.0 and Quarkus 3.21+ auto-configuration included.

@Agent Annotation

One class, one annotation. Endpoints, commands, tools, skill files, conversation memory, and protocol exposure are all auto-wired.

@Coordinator Orchestration

Manage fleets of agents with parallel fan-out, sequential pipelines, conditional routing, and result evaluation.

Durable Workflows

CheckpointStore persists workflow state as parent-chained snapshots. Pause workflows without holding a thread; resume via REST.

Human-in-the-Loop

@RequiresApproval pauses tool execution for human approval. The virtual thread parks cheaply until the client responds.

5 Channels

Slack, Telegram, Discord, WhatsApp, Messenger — alongside the default browser endpoint. Set a bot token and the same @Command + AI pipeline works on every channel.

Admin Control Plane

Real-time dashboard, REST API for governance, runtimes, agents, A2A tasks, and flow graphs, WebSocket event stream, and MCP tools for managing agents.

Observability

OpenTelemetry tracing, Micrometer metrics, and AI token usage tracking. Auto-configured with Spring Boot.

Client SDKs

atmosphere.js with React, Vue, Svelte, and React Native hooks. Streaming, offline queues, auth token refresh.

Who we are

Built by the people who wrote the spec

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.

♦ Java Champions ◆ Apache Committers ◆ JVM NIO/AIO contributors ◆ Open source since 2008
3.7k+ GitHub stars
18 Years in production
253 Versions on Maven Central
Apache 2.0 License
Enterprise Support

Backed by the team that built it

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.

  • Compliance, audited

    OWASP Agentic Top 10, EU AI Act, HIPAA, and SOC 2 evidence matrices ship in-tree and are CI-pinned. Your auditors get a build artifact, not a slide deck.

  • Plan-and-verify

    atmosphere-verifier refuses unsafe LLM-emitted workflows before any tool fires — Meijer Guardians of the Agents (CACM, Jan 2026).

  • MS Agent Governance Toolkit ↗

    Microsoft's YAML rule schema parsed verbatim, same audit_entry JSON shape, same agt verify semantics — drop-in for shops standardising on MS Agent OS.

  • A2A v1.0.0

    Atmosphere ships the released spec. Pre-1.0 method names are aliased server-side so your existing A2A clients keep working through the migration.

  • One contract, nine runtimes

    policyDenyBlocksRuntimeExecute is a build-time invariant for every adapter — you can't add a runtime without proving it honours your governance chain.

Bronze

  • Coverage Business Hours
  • Response (S1) 7 Business Days
  • Response (S2) 10 Business Days
  • Incidents 2 / year
  • Phone Support —
  • Email Support ✓
  • Emergency Patches —
Get a Quote

Silver

  • Coverage Business Hours
  • Response (S1) 1 Business Day
  • Response (S2) 2 Business Days
  • Incidents 10 / year
  • Phone Support —
  • Email Support ✓
  • Emergency Patches —
Get a Quote

Gold

  • Coverage Business Hours
  • Response (S1) 4 hours
  • Response (S2) 1 Business Day
  • Incidents 15 / year
  • Phone Support ✓
  • Email Support ✓
  • Emergency Patches ✓
Get a Quote

Platinum

  • Coverage 24x7
  • Response (S1) 1 hour
  • Response (S2) 4 hours
  • Incidents Unlimited
  • Phone Support ✓
  • Email Support ✓
  • Emergency Patches ✓
Get a Quote
Legacy

Atmosphere 2.x / 3.x Support

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.

Contact Us

Need professional services on a per-hour basis? Contact us for a custom quote.