Eclipse LMOS&AGC: Agentic Computing for Real-World Enterprise Systems
summary
Built for a Deutsche Telekom deployment across ~10 countries and ~200–300 APIs, Eclipse LMOS provides a Kotlin framework (LMOS Arc) plus a declarative ADL layer with an ADL compiler that tree‑shakes prompts, enforces a two‑pass rule, and lets business teams iterate without prompt injection. A runtime (AGC) runs ephemeral and long‑running agents with built‑in telemetry, Kubernetes lifecycle, one Docker/Helm deploy model and a one-API agent compute surface; open-source and live since late 2023, shipped to multiple countries.
AI-written summary · about
chapters (6)
- 0:00Enterprise AI challenges
- 3:40Mental models for agents
- 7:59Designing LMOS platform
- 12:30ADL language for business
- 18:37Agentic compute concept
- 22:52Q&A session
related talks
52mBuilding reliable AI agents with Eclipse LMOS
52mLivecoding: Creating Beautiful Java Code With LLM and Agents
29mEclipse Leda Incubation
46mThe Era of AAP: Ai Augmented Programming using only Java
26mFrom APIs to Agents: Enterprise AI using Java, Ollama & MCP
28mAgentic Development at Enterprise Scale: RAG, MCP & Guardrails
57mPure Java Enterprise AI/LLM Integration (EAI 2.0)
53mHigh Speed Java Development with LLMs and Agents Fast, Clean, Maintainable