Quarkus at AGNTCon + MCPCon 2026

[insectengine]

Event Description: The flagship conference for the open agentic AI ecosystem, uniting builders, contributors, and enterprises across MCP and agentic AI systems.

Date: September 10-11, 2026
Location: Tokyo, Japan
Event Type: In-Person

https://events.linuxfoundation.org/agntcon-mcpcon-japan/

Sessions

Session: Workshop: Enterprise Agentic AI: Architecting Autonomous Java Systems for Production
Speaker(s): Daniel Oh & Kevin Dubois
Date/Time: Thursday, September 10, 2026 16:10 - 17:45 in Hall B
Abstract: Step into the future of enterprise automation by building production-ready agentic AI systems using Java. This hands-on lab guides you through designing scalable multi-agent architectures that seamlessly connect with enterprise infrastructure. You will gain practical experience implementing key design patterns such as sequence, parallel, routing, loop, and supervisor models while enabling direct agent-to-agent (A2A) collaboration. We will also address real-world deployment challenges by integrating human-in-the-loop control points and robust observability features. Leave equipped with functional code and the architectural blueprints needed to bring robust agentic AI into your organization.

Session: Beyond Prototypes: Building Enterprise-scale Agentic Systems
Speaker(s): Kevin Dubois, & Mauricio "Salaboy" Salatino
Date/Time: Friday, September 11, 2026 16:10 - 16:35 in Hall C
Abstract: There has been a lot of progress in agentic frameworks (such as Langchain, CrewAI, Autogen, among others), most of them written in and targeting Python developers. These frameworks allow you to build multi-agent systems that are co-located inside the same application.

That works well for fast experimentation and building prototypes, but production systems live or die on scalability, security, observability and governance. At the end of the day agents are software that we need to ship, run an operate on production, much like any other type of enterprise software.

In this session we will show how to build distributed agentic, MCP-connected systems that are ready for enterprise scale. We'll cover real production patterns such as agentic orchestration patterns, MCP interoperability, agent/tool coordination, observability and tracing and enterprise integration reusing our existing platforms.

Session: Build Your Own Open-Source Claude Code With Local LLMs
Speaker(s): Daniel Oh
Date/Time: Friday, September 11, 2026 16:10 - 16:35 in Hall 1F
Abstract: AI coding assistants are becoming part of everyday development, but many enterprises cannot send source code, internal APIs, or project context to external services. They need the productivity of coding agents while keeping models, repositories, prompts, and actions under their control.

In this session, we’ll show how to build an open-source, Claude Code-like assistant using local or privately hosted LLMs, Models as a Service, OpenCode, and AI guardrails. Developers will be able to explore a codebase, generate changes, review explanations, and trigger controlled actions without exposing sensitive data.

We’ll also cover the guardrails needed for real use: secrets protection, data leakage checks, unsafe command blocking, insecure code detection, and policy-based action control.

You’ll leave with a practical blueprint for building a private, secure coding assistant that improves developer productivity without compromising trust, privacy, or compliance.