by Atmosphere · MCP Server · ★ 3.8k
Atmosphere The real-time engine for AI agents on the JVM. Tokens flow from the LLM runtime to the client through a broadcaster you can filter, gate, and observe — over WebSocket, SSE, long-polling, or gRPC, and out through MCP, A2A, and AG-UI. A plain @Agent is a full deep agent, batteries-included, and Atmosphere handles reconnect, authorization, and governance. <img src="https://github.com/Atmosphere/atmosphere/actions/workflows/ci-js.yml/badge.svg?branch=main" alt="CI:
| Stars | 3,813 |
| Forks | 762 |
| Language | Java |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 65.1101511348012/100 |
| Open Issues | 7 |
| Last Updated | 2026-09-18 |
| Created | 2010-06-30 |
| Platforms | browser, java, mcp |
| Est. Tokens | ~23k |
These tools work well together with atmosphere for enhanced workflows:
Explore other popular mcp server tools:
atmosphere is Portable AI agent runtime for the JVM. One @Agent class runs on Spring AI, LangChain4j, Anthropic, or 9 more behind one SPI. Token streaming, tool calls, human approvals, and governance over WebSocket. It is categorized as a MCP Server with 3.8k GitHub stars.
atmosphere is primarily written in Java. It covers topics such as a2a, acp, agentic-ai.
You can find installation instructions and usage details in the atmosphere GitHub repository at github.com/Atmosphere/atmosphere. The project has 3.8k stars and 762 forks, indicating an active community.
atmosphere is released under the Apache-2.0 license, making it free to use and modify according to the license terms.