Software Development News

A September 2026 roundup of Kyneton news, including the daffodil festival, the skatepark budget, Bald Hill, councillor leave, the agricultural rate, and the end of the local sporting season. Kyneton News Roundup: September 2026 Local Updates

Hellbourne follows Melbourne infrastructure, transport, planning and urban change. Open a suburb, a station, a line, a council or a project. A cost or a completion year is shown with its source and the date it was recorded. Hellbourne: Melbourne, Explained Without the Brochure

Install Superpowers, the open-source skills framework that enforces brainstorm-to-TDD spec-driven development across Claude Code, Cursor, and other agents. Superpowers Quickstart: Install, Workflow, and Tryout

Compare GitHub Spec Kit, AWS Kiro, and Claude Code SDD workflows by portability, setup friction, review gates, and lock-in -- then pick the right setup for your team. GitHub Spec Kit vs Kiro vs Claude Code SDD Workflows

Explore gstack, an opinionated AI engineering stack for Claude Code: its skills, install steps, and how it combines with Superpowers, OpenSpec, and Spec Kit. gstack: AI Software Engineering Stack

llmsystems.dev is live: curated model and GGUF artifact records, llama.cpp, hardware memory classes, and weights-only VRAM bands with explicit evidence labels (SOURCE, POLICY, OBSERVED). Built for people who self-host — not a blog, not fake fit claims. LLM Systems: Operational Reference for Self-Hosted Inference

Compare 12 self-hosted Deep Research systems: GPT Researcher, Onyx, Open WebUI, Khoj, Vane and more. Architectures, local LLM, RAG, licenses. Self-Hosted Deep Research Systems: 12 Tools Compared

In 2026 the open-model efficient frontier sits at 25-34B: Qwen 3.8 27B and Llama 4 Scout deliver near-frontier capability at a fraction of 70B+ cost. The Efficient Frontier of Open Models: Finding the Sweet Spot in 2026

Install Mnemosyne as a local Hermes memory provider, configure recall and retention, and inspect the SQLite store. Mnemosyne for Hermes Agent: Local Memory Quickstart

Agent memory can turn model inferences into future evidence. How those loops form, why they matter, and which write-path controls limit them. Self-Reinforcing Memory Loops in AI Agents: Causes and Fixes

OpenSpec has no native rejected-proposal state. Learn why, what the maintainers decided, and the decision.md convention that stops agents reopening settled investigations. OpenSpec Rejected Proposals: A Decision Memory Convention

Install OpenSpec, the change-centric spec-driven development CLI. Learn the explore-propose-apply-archive loop, brownfield setup, and where it breaks. OpenSpec Quickstart: Install, Workflow, and Common Pitfalls

Migrate OpenClaw to Hermes Agent with dry-run checks, precise memory and skill mapping, secret handling, channel cutover, rollback, and manual fixes. How to Migrate from OpenClaw to Hermes Agent Safely

Complete guide to LLM hosting in 2026. Compare Ollama, llama.cpp, vLLM, TGI, Docker Model Runner, LocalAI and cloud providers. Learn cost, performance, and infrastructure trade-offs. LLM Hosting in 2026: Local, Self-Hosted and Cloud Infrastructure Compared

Compare llama-server and Ollama for local LLM hosting in 2026: GGUF management, APIs, GPU control, KV cache, model lifetime, and migration triggers. llama.cpp vs Ollama in 2026: Which Runtime Should You Run?

Compare AMD ROCm and Vulkan backends for llama.cpp, Ollama, LM Studio, vLLM and TGI, with build commands, verification checks and a practical 2026 verdict. ROCm vs Vulkan for AMD Local LLM Hosting: 2026 Guide

Fit 32K to 128K LLM context into 16 GB VRAM by calculating KV cache cost, choosing cache precision, and tuning llama.cpp, vLLM, or Ollama safely. KV Cache on 16 GB GPUs: Making Long Context Actually Fit

Transformers are hitting walls in compute, data, and energy. State space models (Mamba), diffusion language models, and JEPA world models may come next. What Comes After LLMs? Mamba, Diffusion & World Models

Backup and restore a self-hosted Gitea server with the built-in gitea dump command, plus Docker steps, restore-repo, and troubleshooting tips. Backup and Restore Gitea server

Choose between Agent Skills and MCP servers using connectivity, credentials, context cost, security, and a practical thin-server pattern for AI agents. Agent Skills vs MCP Servers: Decision Framework

Learn when to migrate from Ollama to vLLM. Migration signals, planning steps, Docker Compose setup, and a practical checklist for moving your local LLM server. Ollama to vLLM: When to Migrate Your Local LLM Server

Install Superpowers, the open-source skills framework that enforces brainstorm-to-TDD spec-driven development across Claude Code, Cursor, and other agents. Superpowers Quickstart: Install, Workflow, and Tryout