Agentic AI on Java 25 & Quarkus 2026

Enterprise AI.
Java-fast.

We design and ship AI agents and cloud-native backends on the JVM — secure, observable and built to run in production, not just in a demo.

Our stack

› Java 25 LTS › Quarkus › LangChain4j › MCP › GraalVM › AWS › OpenShift

What we do

From JVM core
to AI agents.

Robust, scalable backend systems and intelligent applications — from cloud-native microservices to AI agents that act safely on your enterprise data and systems.

Agentic AI & MCP NOW

AI agents that don't just answer, but act: calling your APIs, querying your data and following your business rules. Built with LangChain4j and the Model Context Protocol, with guardrails, evaluation and full traceability.

LangChain4j MCP Server & Client RAG Guardrails Evals

Quarkus

Cloud-native Java with fast startup, low memory and native builds — ideal for containers and serverless.

Native Image Reactive OpenAPI

Java & JVM

Enterprise-grade backends on modern Java — virtual threads, records, pattern matching — designed to last.

Java 25 JPA REST

Modernisation & Migration

Moving legacy Java EE and Spring applications to Quarkus and current Java versions — step by step, without a big-bang rewrite.

Java EE → Quarkus Spring → Quarkus Java 8/11/17 → 25

Cloud & Platform

Containerised, observable services on AWS and OpenShift — with infrastructure as code, CI/CD and OpenTelemetry from day one.

AWS OpenShift Kubernetes OpenTelemetry

How we work

Built for production.
Not just demos.

  1. 01

    Discover

    We identify where AI genuinely adds value in your processes — and where it doesn't.

  2. 02

    Prototype

    A working slice against your real data and systems in weeks, measured against clear success criteria.

  3. 03

    Productionise

    Security, guardrails, evals, observability and cost control — everything a demo skips.

  4. 04

    Operate & hand over

    Running on your AWS or OpenShift platform, documented and maintainable by your own team.

// an AI agent with tools — Quarkus does the rest

@RegisterAiService(tools = OrderTools.class)
@McpToolBox("erp")
@InputGuardrails(PiiFilter.class)
public interface SupportAgent {

  @SystemMessage("""
      You are an enterprise support agent.
      Use the tools. Never guess order data.
      """)
  String chat(@MemoryId String session,
              @UserMessage String question);
}

Selected work

Real projects.
Real constraints.

From regulated healthcare to our own product at sea — where security, standards and reliability are not optional.

Healthcare ITsince 2024

Laboratory ordering platform for medical practices and labs

Challenge

Replace a legacy desktop application with a modern platform — running in the cloud and on appliances inside medical practices, without losing existing data.

Solution

Built end-to-end: Quarkus microservices on Java 25, web-component frontends and a central hub that syncs practices, forms and lab catalogues. Lab data exchange (LDT), standard forms with barcodes, a guided migration from the legacy system and AI-based suggestions of lab tests from diagnoses.

Result

One codebase for cloud and on-prem, deployed via GitOps on OpenShift and monitored with Grafana dashboards and alerting.

Healthcare2023 – 2024

High-security Matrix messenger with a Java security layer

Challenge

Secure, standards-based messaging for healthcare organisations that meets the strict security requirements of a national healthcare network — operated in the cloud.

Solution

A high-security layer in Java and Quarkus in front of the Matrix homeserver: every request is authenticated and filtered, federation is limited to approved servers from a centrally maintained list, and participants are looked up in a FHIR directory. Plus self-service registration with Keycloak and OpenID Connect and a browser client built with web components.

Result

A containerised messaging platform on an open standard, with full control over who can sign in, what may be called and which servers may federate.

In-house productMarine2026ychtos.com ↗

ychtos — connected navigation and monitoring for luxury yachts

Challenge

Bring all of a luxury yacht's data together — instruments, AIS, energy, weather and cameras — on every device on board, and keep it working at sea without internet.

Solution

A Quarkus application on a compact onboard server reads NMEA 0183 and AIS, Victron energy data via MQTT and onboard sensors, and streams everything live to the browser on iPad, laptop and phone. Offline nautical charts, logbook, routes, anchor and watch alarms, weather and boat guard with push notifications.

Result

Everything safety-relevant runs on the server and survives a restart — alarms sound in every browser and on the onboard speaker. A companion to certified navigation equipment, not a replacement.

Principles

AI as a feature,
not a buzzword.

What separates an impressive demo from a system your business can rely on.

/ grounded

Grounded in your data

Answers based on your documents and systems, with sources — not on model guesswork.

/ sovereign

Your data stays yours

EU hosting, private models or on-prem via Ollama or vLLM — aligned with GDPR and the EU AI Act.

/ measured

Measured outcomes

Evals, tracing and cost metrics make quality and spend visible — before and after go-live.

/ lean

Performance that matters

Native builds and lean JVM services start in milliseconds and keep cloud bills small.

Let's work together

Let's ship your next
enterprise project.

Greenfield system, Quarkus migration or your first production AI agent — tell us about your project and we'll get back to you.