| Eclipse Foundation Adds Agentic Functionality To Eclipse LMOS |
| Tuesday, 28 October 2025 |
|
The Eclipse Foundation has added Agent Definition Language (ADL) functionality to the Eclipse LMOS (Language Model Operating System) project. Eclipse LMOS is an open source platform for orchestrating intelligent AI agents. It has two components, the Eclipse LMOS ARC Agent Framework & ADL, and the Eclipse LMOS platform.
The framework and ADL is a JVM-native agent framework with a Kotlin runtime and visual interface for defining agent behavior collaboratively. The LMOS platform is an open, vendor-neutral orchestration layer for agent lifecycle management, discovery, semantic routing, A/B testing, and observability. ADL provides a structured, model-agnostic framework that can be used by business and engineering teams to co-define agent behavior in a consistent, maintainable, and versionable way. The Eclipse team says that traditional prompting for AI agents is complex, inconsistent, and brittle. Each new LLM release or behavior change requires re-tuning prompts—a process that is time-consuming and hard to scale. ADL solves this by introducing a structured, standardized, and model-agnostic way to define agent behavior. The goal of the LMOS project is to create a sovereign, open platform where AI agents can be developed, deployed, and integrated seamlessly across networks and ecosystems. The framework is built on open standards such as Kubernetes. "Agentic AI is redefining enterprise software, yet until now there has been no open source alternatives to proprietary offerings," according to Mike Milinkovich, executive director of the Eclipse Foundation. "With Eclipse LMOS and ADL, we're delivering a powerful, open platform that any organization can use to build scalable, intelligent, and transparent agentic systems." Eclipse LMOS runs on technologies including Kubernetes, Istio, and JVM-based applications. The foundation says it will empower non-technical users to shape agent behavior. Business domain experts, not just engineers, can directly encode requirements into agents, ensuring that agent behavior accurately reflects real-world domain knowledge. Arun Joseph, Eclipse LMOS project lead, said the framework eliminates the fragility of prompt-based design and gives enterprises a practical path to scale agentic AI using their existing teams and resources. Eclipse LMOS's open architecture is part of Eclipse's open ecosystem that the team says invites developers, data scientists, and organizations to collaborate and shape the future of Multi-Agent Systems. Its AI agent collaboration helps with problem-solving because LMOS orchestrates the interactions with advanced routing based on the user's intent or goals, allowing agents to work together seamlessly within a single, unified system. The framework also offers cloud native scalability that dynamically scales from a few agents to hundreds. It is built with modularity at its core, so organizations can integrate new Agents in their preferred development language or framework. The framework is also designed to be extensible, letting organizations define clear specifications to extend its ecosystem. LMOS is designed to be multi-tenant capable from the ground up, enabling the efficient management of multiple tenants and agent groups within a single infrastructure.
More InformationRelated ArticlesEclipse Launches Dataspace Working Group Eclipse Foundation Forms Open VSX Working Group To be informed about new articles on I Programmer, sign up for our weekly newsletter, subscribe to the RSS feed and follow us on Twitter, Facebook or Linkedin. 
Comments
or email your comment to: comments@i-programmer.info |
