The CoddyKit Blog

Ideas, tutorials, and stories from the world of code.

Hand-picked deep dives on programming, AI tooling, and software craft — written by the CoddyKit team for curious learners.

All articles
I

Is MCP Dead? Why Developers Are Rethinking the "USB-C of AI"

A critical look at the growing "MCP is dead" debate among developers. We break down context bloat, reliability issues, security c…

5 min read
B

Build Durable Workflows with SQLite: A Step-by-Step Guide

A complete tutorial on building a durable workflow engine using SQLite and Python — with crash recovery, automatic retries, event…

7 min read
T

The 5 Developer Skills That Will Actually Matter in 2026 (That Aren't Frameworks)

Frameworks come and go, but the developer skills that actually drive career growth in 2026 are meta-skills: systems thinking, cod…

4 min read
S

Speculative Decoding for LLMs: Accelerate Inference 2-3× with Draft Models

Speculative decoding uses a small draft model to propose multiple tokens ahead, then verifies them in parallel with the target mo…

6 min read
7

7 Best AI Coding Assistants Compared in 2026 — Which One Should You Choose?

Compare the top 7 AI coding assistants in 2026: Claude Code, GitHub Copilot, Cursor, Codex, Gemini CLI, OpenClaw, and Devin. Find…

4 min read
C

Claude Opus 4.8 Is Here — And It Changes What "AI Coding Assistant" Means

Anthropic launched Claude Opus 4.8 with dynamic workflows (hundreds of parallel subagents), effort control, and 4× fewer silent b…

5 min read
H

How to Build an AI-Ready Web Scraper with Crawl4AI: A Step-by-Step Guide

A step-by-step tutorial on using Crawl4AI to scrape websites and produce clean, LLM-ready Markdown and structured JSON output. Co…

4 min read
T

The Developer Skill Stacking Strategy: How Combining Complementary Skills Creates Unstoppable Career Leverage

Discover how combining complementary skills - code + communication, domain expertise, design sense, or business acumen - creates…

6 min read
S

Speculative Decoding: 2x Faster LLM Inference Without Quality Loss

Learn how speculative decoding achieves 2-3x LLM inference speedup with zero quality loss. Complete tutorial with Python implemen…

7 min read
7

7 Open-Source AI Developer Tools Replacing Paid SaaS in 2026

Open-source AI developer tools are replacing expensive SaaS products in 2026. This listicle covers 7 trending tools — from code a…

4 min read