Tools
18 articlesThe practical stack: frameworks, SDKs and platforms.
Installing Codex CLI: a basic guide
Install OpenAI Codex CLI on macOS, Linux, or Windows, sign in with ChatGPT or an API key, and run your first coding session.
Installing Cursor CLI: a basic guide
Install Cursor CLI (cursor-agent), the terminal coding agent from Cursor, on macOS, Linux, or Windows, sign in, and run your first session.
Installing Antigravity CLI: a basic guide
Install Antigravity CLI (agy), Google's terminal surface for Antigravity agents, on macOS, Linux, or Windows, and run your first task.
Installing opencode: a basic guide
Install opencode, the open-source terminal coding agent, on macOS, Linux, or Windows, connect a provider, and run your first session.
Installing herdr: a basic guide
Install herdr, the terminal workspace manager for coding agents, on macOS, Linux, or Windows, and start your first workspace.
Subagents in Claude Code
Claude Code subagents run a task in their own isolated context and return only the summary, so they don't clutter your main conversation.
Testing as Spec With Claude Code
How to ask Claude Code for tests that read like a human spec and actually validate behavior, instead of just passing.
What is Claude Design
Claude Design is Anthropic Labs' tool for creating designs and prototypes by talking to Claude; it remembers your visual system across projects.
Screen-by-Screen Iteration in Stitch
In Stitch, refining a design one screen at a time with scoped prompts gives you control and doesn't risk what already worked.
Stitch vs. Figma: When to Use Each
Stitch is for fast AI-driven UI exploration; Figma is for precision and collaboration. When to choose each in an AI-first workflow.
Stitch and the Infinite Canvas
Google Stitch generates UI screens from prompts on an infinite canvas, built to explore and compare variants at a glance.
Getting Started With v0 by Vercel
v0 is Vercel's generative UI tool that creates production-ready React components from text prompts. Go from zero to your first component in 5 minutes.
Guide to Langfuse and Helicone for LLM Observability
Langfuse and Helicone are open-source platforms that bring tracing, cost monitoring, and debugging to LLM applications in production.
Introduction to vLLM: Optimizing Inference Performance
vLLM is an open-source inference engine that accelerates LLMs using PagedAttention, dynamic batching, and quantization for production-scale serving.
How to Run Local Models with Ollama in Your Development Environment
Ollama lets you download, run, and manage LLMs locally without relying on external APIs or an internet connection.
Introduction to AI Extensions in VS Code
Copilot, Cody, and Continue bring LLMs directly into your editor. Learn how they work and how to pick the right one for your workflow.
How to install Claude Code
Step-by-step guide to installing Claude Code on macOS, Linux, and Windows. Covers all installation methods, system requirements, and initial setup.
Warp — Agentic Development Environment in the Terminal
Warp is a modern Rust-based terminal that integrates coding agents, code review, and orchestration of local and cloud agents in one surface.