VirtusLab's Articles

All Artificial Intelligence Business insights Frontend Engineering Backend Engineering Data Engineering Scala Cloud Engineering Basel Knowledge Hub

Artificial Intelligence|Published: Mar 25, 2026

GitHub All-Stars #16: Project N.O.M.A.D. - Civilization in a Docker Container

Welcome to GitHub All-Stars, our biweekly series where we pick a trending or freshly minted open-source project and put it under the microscope. We focus on new, relatively unknown gems - not another breakdown of the latest React release (because let's be honest, the world has enough of those). This time, we're looking at a project that lives at an unusual intersection of prepper culture, self-hosting enthusiasm, and edge computing philosophy. And it just exploded on Hacker News.

Artificial Intelligence|Published: Mar 25, 2026

AI and the Future of Monorepos: An interview with Piotr Kukiełka

For years, the industry moved away from monorepos toward microservices and smaller repositories. Recently, however, the conversation has started to shift again - and AI may be one of the reasons. As AI tools become part of everyday development workflows, the way engineers interact with large codebases is changing. Piotr Kukiełka shares his perspective on how large codebases work in practice and why AI might influence how companies think about monorepos.

Artificial Intelligence|Published: Mar 24, 2026

Interview with Artur Skowroński, Head of Application Development and the lead of the VISDOM project

What if the biggest blocker to AI-driven development isn’t the AI itself but everything around it? Artur Skowroński, our Head of Application Development, talks about the most common issues enterprises have stumbled upon over the last few years, and how VirtusLab is working to remove them. This is a sneak peek into VISDOM: a platform designed for a world where AI produces massive amounts of code, and organizations need a way to truly understand, trust, and manage it. Read on to discover how it all comes together.

Artificial Intelligence|Published: Mar 24, 2026

Secure by design for Agentic AI in Insurance

Learn how insurers can secure AI agent platforms through threat modeling frameworks like OWASP, MAESTRO, and MITRE ATLAS. This guide covers prompt injection risks, trust boundaries, and compliance with DORA and EU AI Act.

Artificial Intelligence|Published: Mar 11, 2026

GitHub All-Stars #15: jCodeMunch MCP - When your Agent stops reading and starts navigating

This is GitHub All-Stars - a series about open-source gems that deserve a closer look, before they become tomorrow's mainstream. Today, we're looking at a project that tackles what is arguably the most expensive waste in the entire AI-assisted coding workflow: context window abuse.

Artificial Intelligence|Published: Mar 10, 2026

Agents for Legacy Code migration

The traditional large, legacy system migration can cost multiple times the yearly company revenue and still yield limited versions of the original system functionality. However, with the help of AI, it can change. The migration process might become faster, cheaper, and smoother.

Artificial Intelligence|Published: Mar 6, 2026

How We Got FP16 GPU Tests Running on GitHub Actions - Without a GPU

This post is about the practical challenges of getting GPU-targeting code tested in environments without GPU hardware - specifically GitHub Actions. The project behind it uses Project Babylon / HAT (an experimental OpenJDK fork that compiles Java to GPU kernels), but the lessons apply to anyone doing OpenCL, CUDA, or heterogeneous compute work in CI.

Artificial Intelligence|Published: Feb 25, 2026

GitHub All-Stars #14: NanoClaw - Your Personal AI Butler in a Container Cage

Today's subject has become one of the most talked-about open-source projects in the AI agent space, racking up over 11,000 GitHub stars in less than a month. We're looking at NanoClaw by Gavriel Cohen - a lightweight, container-isolated personal AI assistant that connects to WhatsApp (and Telegram, Discord, Slack, Signal) and runs on Anthropic's Agent SDK. Written in TypeScript, MIT-licensed, and built around one radical premise: the software that hosts powerful AI agents should be simple enough to read in eight minutes.

Artificial Intelligence|Published: Feb 16, 2026

How to improve your RAG: Move Beyond Flat Vector Stores

Most of the time, the knowledge base we want to chat and reason about with an LLM has strong inter-relations. Even the famous PageRank algorithm, which gave Google a competitive advantage and made it ahead of others, is based on the quantity and quality of links between websites. The relations within a knowledge base are crucial to fully understand it. The problem with classical RAG is that it chunks the text, discarding all internal relations. So can we do better?

Artificial Intelligence|Published: Feb 11, 2026

GitHub All-Stars #13: Matchlock - Your Agent's Bulletproof Cage (With Room Service)

Today's project dropped on Hacker News frontpage just days ago and instantly sparked one of the most interesting security discussions I've seen in a while. We're looking at Matchlock by Jingkai He - a CLI tool for running AI agents in ephemeral microVMs with network allowlisting and secret injection via MITM proxy. Built to answer a question that every developer running claude --dangerously-skip-permissions should be asking: "What's the worst that could happen?"

Artificial Intelligence|Published: Feb 6, 2026

NeurIPS 2025 Best Papers TL;DR part 2: 1000 Layer Networks

In the second part, Adam will focus on reinforcement learning networks by summarizing the "1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities", an article featured in NeurIPS 2025.

Artificial Intelligence|Published: Jan 29, 2026

Do you need an AI Agent?

Agents are LLMs that move in the partially observed environment, interact with it, reason, plan, act, and adapt to the changing environment. They need to use tools to gather information in the iterative cycles. The information required to complete the task is hidden and requires online querying or tool use to obtain it. If your environment is fully observed and determined, tasks are repetitive, and you don’t need to adapt to unplanned changes, a simple LLM pipeline is just enough.

1 2 3 4 5