Articles, one at a time.
Every piece here was commissioned, drafted, reviewed in public, and merged. No content mills, no auto-published slop.
Gemini 3.1 Ultra: Long Context and Multimodal Dev Guide
A practical guide to Gemini 3.1 Pro's 1M-token context window, native multimodal inputs, sandboxed code execution, and API setup for 2026.
Read →
Langfuse: Self-Host LLM Observability for Free — 2026 Guide
Deploy Langfuse free with Docker Compose. Open-source LLM observability covering traces, evals, prompt management, and Kubernetes scaling.
Read →
LiteLLM: One Proxy for 140+ LLMs — Setup & Cost Guide
LiteLLM unifies 100+ LLM APIs behind one OpenAI-compatible endpoint. Learn to self-host, control costs, and set provider fallbacks in 2026.
Read →
GLM-5.1: Open-Source Model That Tops SWE-Bench Pro
GLM-5.1 is a 754B MoE open-weight model with MIT license that scored 58.4 on SWE-Bench Pro, beating GPT-5.4 and Claude Opus 4.6.
Read →
Goose by Block: The Free, Open-Source AI Agent with 29K Stars
An in-depth review of Goose, Block's Apache 2.0 AI agent. Compare it to Claude Code, explore MCP extensions, Recipes, and local Ollama setup.
Read →
Microsoft Agent Framework 1.0: Build AI Agents in .NET and Python
Microsoft Agent Framework 1.0 ships production-ready AI agent orchestration for .NET and Python. Full MCP support, YAML agents, multi-provider LLMs.
Read →
Claude Mythos Preview: Developer Guide for 2026
Claude Mythos hits 93.9% SWE-bench and 83.1% CyberGym. Here's what developers need to know about access, benchmarks, and what's coming next.
Read →
Google ADK: Build Multi-Agent Systems with Python
Learn to build multi-agent AI systems with Google's Agent Development Kit (ADK). Code-first Python guide covering setup, orchestration, A2A, and deployment.
Read →
OpenAI Codex CLI: Terminal Coding Agent Setup Guide 2026
Complete guide to OpenAI Codex CLI — setup, safety modes, sandboxing, and how it compares to Claude Code in 2026.
Read →
AI Coding Market Share 2026: Who's Winning?
Claude Code holds 54% of the AI coding market. Cursor hit $2B ARR. Copilot leads enterprise. Here's what the 2026 numbers actually mean.
Read →
Grok 4 Multi-Agent Architecture: Dev Guide 2026
Learn how xAI's Grok 4.20 four-agent inference system works, what it costs, and how to integrate it into your development workflow in 2026.
Read →
Qwen3 Review: Hybrid Thinking Modes and MoE Architecture Explained
Qwen3 ships hybrid thinking/non-thinking modes, MoE variants up to 235B, and Apache 2.0 licensing. Developer guide with benchmarks, setup, and API pricing.
Read →