atmosphere

A real-time transport layer for Java AI agents, supporting WebSocket, SSE, gRPC, and WebTransport/HTTP3.

MCPDevOpen sourceJavaAI 代理实时传输

Type: MCP
Transport: http
Open source: Yes
GitHub Stars: ★ 3.8k
Source: mcp-github
Repository: github.com/Atmosphere/atmosphere

Overview

Atmosphere is a real-time transport layer for Java AI agents. It enables developers to build once and deliver across WebSocket, SSE, gRPC, and WebTransport/HTTP3 using the @Agent annotation. Atmosphere supports MCP, A2A, and AG-UI protocols, offering runtime scheduling, reconnection, authorization, observability, and governance capabilities. Ideal for teams needing to stream and manage AI agents as production services.

Capabilities

▪Supports WebSocket, SSE, gRPC, and WebTransport/HTTP3
▪Provides @Agent annotation to simplify development
▪Supports MCP, A2A, and AG-UI protocols
▪Runtime scheduling and reconnection
▪Authorization and observability
▪Governance paths and policy management

Use cases

Building real-time streaming AI agentsDelivering AI agents across multiple protocolsManaging and monitoring AI agent behaviorEnabling persistent sessions and resume from breakpoints

Setup

Requires: MavenNode 环境

Add the dependency in Maven: `<dependency> <groupId>org.atmosphere</groupId> <artifactId>atmosphere-runtime</artifactId> <version>latest version</version> </dependency>`

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.

FAQ

What transport protocols does Atmosphere support?

WebSocket, SSE, gRPC, and WebTransport/HTTP3.

How do I use Atmosphere to build an AI agent?

Declare behavior using the @Agent annotation; Atmosphere handles runtime scheduling and other aspects automatically.

Related skills

gemini-cli

Gemini CLI is an open-source AI agent that brings Gemini's powerful capabilities directly into the terminal.

MCP

private-gpt

Provides a complete API layer for local models, supporting RAG, skills, tools, and more.

MCP

planning-with-files

File-based persistent planning skill, ideal for AI coding agents and long-running tasks.

Agent Skill

scientific-agent-skills

Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.

Agent Skill

susi_alexa_skill

A skill that enables question-and-answer interactions between Alexa and Susi AI.

Agent Skill

claude-context

Provides code search capabilities for Claude Code, turning the entire codebase into context.

MCP