Rost Glukhov | AI Systems & Infrastructure

Discord becomes a serious integration surface when you treat it like one: a place where systems publish events, humans make decisions, and automation continues the workflow.

Chat platforms have evolved far beyond messaging tools.

The quiet loophole that powered a wave of agent experimentation is now closed.

Vane is one of the more pragmatic entries in the “AI search with citations” space: a self-hosted answering engine that mixes live web retrieval with local or cloud LLMs, while keeping the whole stack under your control.

Text Generation Inference (TGI) has a very specific energy.

Here I am comparing speed of several LLMs running on GPU with 16GB of VRAM, and choosing the best one for self-hosting.

Australia has RTX 5090 stock.

Ollama is at its happiest when it is treated like a local daemon: the CLI and your apps talk to a loopback HTTP API, and the rest of the network never finds out it exists.

Logs are a debugging interface you can still use when the system is on fire.

Ollama works great on bare metal.

Running Ollama behind a reverse proxy is the simplest way to get HTTPS, optional access control, and predictable streaming behaviour.

Netlify is one of the most developer-friendly ways to ship Hugo sites and modern web apps with a production-grade workflow: preview URLs for every pull request, atomic deploys, a global CDN, and optional serverless and edge capabilities.

Apache Flink is a framework for stateful computations over unbounded and bounded data streams.

Neo4j is what you reach for when the relationships are the data.

Static sites and blogs change whenever you deploy.

Putting email on your own domain sounds like a weekend DNS task.

SGLang is a high-performance serving framework for large language models and multimodal models, built to deliver low-latency and high-throughput inference across everything from a single GPU to distributed clusters.

Soon you are juggling vLLM, llama.cpp, and more—each stack on its own port.

Apache Kafka 4.2.0 is the current supported release line, and it’s the best baseline for a modern Quickstart because Kafka 4.x is fully ZooKeeper-free and built around KRaft by default.

Oh My Opencode promises a “virtual AI dev team” — Sisyphus orchestrating specialists, tasks running in parallel, and the magic ultrawork keyword activating all of it.

I have tested how OpenCode works with several locally hosted on Ollama and llama.cpp LLMs, and for comparison added some Free models from OpenCode Zen.

The biggest capability jump in OpenCode comes from specialised agents: deliberate separation of orchestration, planning, execution, and research.

OpenHands is an open-source, model-agnostic platform for AI-driven software development agents.

LocalAI is a self-hosted, local-first inference server designed to behave like a drop-in OpenAI API for running AI workloads on your own hardware (laptop, workstation, or on-prem server).

Oh My Opencode turns OpenCode into a multi-agent coding harness: an orchestrator delegates work to specialist agents that run in parallel.

Airtable is best thought of as a low‑code application platform built around a collaborative “database-like” spreadsheet UI - excellent for rapidly creating operational tooling (internal trackers, lightweight CRMs, content pipelines, AI evaluation queues)…

LLM inference looks like “just another API” — until latency spikes, queues back up, and your GPUs sit at 95% memory with no obvious explanation.

OpenClaw is a self-hosted AI assistant designed to run with local LLM runtimes like Ollama or with cloud-based models such as Claude Sonnet.

AWS S3 remains the “default” baseline for object storage: it is fully managed, strongly consistent, and designed for extremely high durability and availability.

Temporal is an open-source, enterprise-grade workflow engine that enables developers to build durable, scalable, and fault-tolerant workflow applications using familiar programming languages like Go.

Garage is an open-source, self-hosted, S3-compatible object storage system designed for small-to-medium deployments, with a strong emphasis on resilience and geo-distribution.

LLM systems fail in ways that traditional API monitoring cannot surface — queues fill silently, GPU memory saturates long before CPU looks busy, and latency blows up at the batching layer rather than the application layer.

Chunking is the most under-estimated hyperparameter in Retrieval ‑ Augmented Generation (RAG): it silently determines what your LLM “sees”, how expensive ingestion becomes, and how much of the LLM’s context window you burn per answer.

Choosing the right browser automation stack and webscraping in Go affects speed, maintenance, and where your code runs.

Desktop launchers on Ubuntu 24 (and most Linux desktops) are defined by .desktop files: small, text-based config files that describe an application or link.

The AWS Free plan is not working for me and Pay-as-you-go is hidden for new CloudFront Distributions on AWS Console .

Choosing the right browser automation stack in Python affects speed, stability, and maintenance.

Two strong options for building terminal user interfaces today are BubbleTea (Go) and Ratatui (Rust).

Self-hosting LLMs keeps data, models, and inference under your control-a practical path to AI sovereignty for teams, enterprises, nations.

Running large language models locally gives you privacy, offline capability, and zero API costs.

The Python ecosystem this month is dominated by Claude Skills and AI agent tooling.

The Rust ecosystem is exploding with innovative projects, particularly in AI coding tools and terminal applications.

The Go ecosystem continues to thrive with innovative projects spanning AI tooling, self-hosted applications, and developer infrastructure.

This comprehensive guide provides background and a detailed comparison of Anaconda, Miniconda, and Mamba - three powerful tools that have become essential for Python developers and data scientists working with complex dependencies and scientific computing…

The Linux display server landscape has been evolving dramatically over the past decade.

Today we are looking at the top-level consumer GPUs, and RAM modules.

One of the most essential tools for Linux users is the terminal emulator.

Open WebUI is a powerful, extensible, and feature-rich self-hosted web interface for interacting with large language models.

Melbourne’s tech community continues to thrive in 2026 with an impressive lineup of conferences, meetups, and workshops spanning software development, cloud computing, AI, cybersecurity, and emerging technologies.

vLLM is a high-throughput, memory-efficient inference and serving engine for Large Language Models (LLMs) developed by UC Berkeley’s Sky Computing Lab.