LLM Infrastructure

5 pieces on LLM Infrastructure, including 1 step-by-step guide.

Guides

Shan • 2026-05-15

Claude CodeOllamaOpenRouterLiteLLMAI EngineeringLLM Infrastructure

The Developer's Guide to Running Claude Code for Free: Ollama, OpenRouter, and Local Proxies

Stop paying for Anthropic tokens. Learn the engineering patterns required to redirect Claude Code's CLI to local models via Ollama or high-parameter free models on OpenRouter.

News & Analysis

news

Shan • 2026-08-23

NeMo GuardrailsAI SafetyAgentic AILLM InfrastructureEnterprise AI

NeMo Guardrails: Three Interception Points for Production LLM Safety

A developer tutorial builds FinBot on gpt-4o-mini with deterministic regex rails, LLM self-checks, retrieval filtering, and a six-probe coverage report.

news

Shan • 2026-08-22

NvidiaAgentic AIBenchmarksOpen WeightsLLM Infrastructure

Nvidia's AVO Harness Takes Claude Opus 5 from 30% to 100% on ARC-AGI-3

Nvidia's custom AVO harness lifted Claude Opus 5 from 30% to 100% on ARC-AGI-3 — without changing the model at all.

DeepSeek Harness v0.1: A Plugin-First MIT-Licensed Agent Framework

news

Shan • 2026-08-17

DeepSeekAgent FrameworksOpen SourceDeveloper ToolsLLM Infrastructure

DeepSeek Harness v0.1: A Plugin-First MIT-Licensed Agent Framework

DeepSeek releases Harness v0.1 under MIT: a developer-preview agent framework where every capability — models, tools, UI — is a swappable Cordis plugin.

news

Shan • 2026-08-09

AI AgentsNVIDIAPythonOpen SourceBenchmarksLLM Infrastructure

NOOA: NVIDIA's Object-Oriented Agent Framework Explained

NVIDIA open-sources NOOA, a Python framework that collapses prompt templates, tool schemas, and workflow graphs into one class—with 82.2% on SWE-bench Verified.