AI Coding

AI agent architecture is starting to split into two layers.

The A2A Protocol, short for Agent2Agent Protocol, is an open standard for communication between independent AI agent systems.

Design decisions for production LLM systems — routing, cost, guardrails, and multi-model orchestration. The layer between running models and building reliable AI applications.

Single-model systems are simple. Multi-model systems are powerful. The challenge isn’t choosing models — it’s designing the architecture that orchestrates them.

A production AI assistant is not “an LLM with a prompt”. It is a system that accepts intent, keeps state, decides when to retrieve or act, and exposes enough runtime detail to debug failures.

Most LLM “structured output” tutorials are unserious. They teach you to ask for JSON politely and then hope the model behaves. That is not validation. That is optimism with braces.

This page is a practical reference for agentic LLM inference tuning (temperature, top_p, top_k, penalties, and how they interact in multi-step and tool-heavy workflows).

Most teams misuse Claude Skills in one of two ways. They either turn SKILL.md into a dumping ground, or they never graduate from giant copy-pasted prompts.

Claude Code is not autocomplete with better marketing. It is an agentic coding tool: it reads your codebase, edits files, runs commands, and integrates with your development tools.

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. Everything downstream still wants one /v1 base URL; otherwise you keep shuffling ports, profiles, and one-off scripts. llama-swap is the /v1 proxy before those stacks.

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. It lets an agent behave more like a coding partner than a simple autocomplete tool.

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