Blog

Insights, tutorials, and best practices from our team — practical knowledge you can apply today.

Soverius AI is now maintaining CopilotKit for Angular

Agentic, generative UI for Angular — a maintained, MIT-licensed package, shown with a small Angular + NgRx demo.

AngularCopilotKitGenerative UI
Murat SariMurat SariRainer HahnekampRainer Hahnekamp
Jul 10, 2026

Knowledge in a Browser Tab: Fully Local RAG with Gemma 4

Retrieval-Augmented Generation entirely client-side: with Angular, Transformers.js, WebGPU, and Google's new on-device model Gemma 4 E2B

AIRAGGemma 4
Murat SariMurat Sari
Jun 26, 2026
Reviewed byRainer HahnekampRainer Hahnekamp

Build a local AI coding agent from scratch

Build a local AI coding agent from scratch — Gemma 4 on llama.cpp, three tools, one loop — then learn why running it unsandboxed is dangerous and how NVIDIA OpenShell contains it.

localllmnvidia
Murat SariMurat Sari
Jun 11, 2026
Reviewed byRainer HahnekampRainer Hahnekamp

What is an Agent Harness?

Learn what an Agent Harness is, why it matters, and how it improves LLMs through tools, context management, agent runtimes, guardrails, and intent alignment.

AIHarnessAgent
Rainer HahnekampRainer Hahnekamp
May 28, 2026
Reviewed byMurat SariMurat Sari

Behind the curtain of A2UI: how and why it could work

Benchmarking 14 local LLM configurations on Google's A2UI generative-UI protocol on a DGX Spark. The cliff between what works and what fails is sharper than expected.

A2UIGenerative UILLM Benchmark
Murat SariMurat Sari
May 12, 2026
Reviewed byRainer HahnekampRainer Hahnekamp

AI Fundamentals: How LLMs Work and Their Limitations

A deep dive into how AI models really work, from pre-training and inference to Chain of Thought, agents, and the emerging field of Harness Engineering.

AILLMHarness Engineering
Rainer HahnekampRainer Hahnekamp
Apr 23, 2026
Reviewed byMurat SariMurat Sari