Software Development News

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?