The Taku Blog
Ideas worth building on.
Stories, product notes, and perspectives on how AI gets discovered, used, remixed, and shared.
October 5, 2026
Claude Code Headless Mode: Run claude -p in Scripts
Claude Code headless mode is the -p flag. How to pipe input, pick an output format, limit tools and turns, resume sessions, and run it in CI.

October 5, 2026
Claude Code JetBrains Plugin: Install and Setup
How to run Claude Code in JetBrains IDEs: install the plugin, connect with /ide, use IDE diffs and selection context, plus WSL and remote notes.

October 5, 2026
Claude Code on the Web: How Cloud Sessions Work
Claude Code on the web runs sessions on Anthropic's cloud, not your laptop. How to start one, what GitHub does, and what keeps running when you close the tab.

October 5, 2026
Claude Code Permissions: Modes, Rules, settings.json
How Claude Code permissions work: the six permission modes, allow, ask and deny rules, which settings file wins, /permissions, and where the sandbox fits.

October 5, 2026
Claude Code Slash Commands: Built-In and Custom
Claude Code slash commands explained: what the built-in ones do, where custom commands live, and how they relate to skills now that the two have merged.

October 5, 2026
Claude Code vs Lovable: App Builder or Coding Agent?
Lovable generates and hosts your web app. Claude Code edits a codebase you own. How to choose, and how the Lovable-to-GitHub-to-Claude Code handoff works.

October 5, 2026
Context Window Explained: Why the AI Forgets
What a context window is, how tokens fill it, why long chats go wrong, and how compaction, memory, and retrieval differ. Habits that keep AI useful.

October 5, 2026
Dify vs Langflow: App Platform or Flow Builder
Dify vs Langflow compared on licence, RAG, publishing, MCP and self-hosting. Dify ships a finished AI app; Langflow is a Python-based visual builder.

October 5, 2026
Google Antigravity vs Cursor: Agent-First or Editor-First?
Antigravity is now a family of agent-first surfaces from Google. Cursor is an AI editor owned by SpaceX. Here's how they differ as of October 2026.

October 5, 2026
MCP Security Risks: What to Check Before You Connect
MCP security risks as the spec itself names them: code execution, prompt injection, token misuse, and untrusted servers, plus a checklist before you connect.

October 5, 2026
Mistral vs ChatGPT: Open Weights, EU Data, and Breadth
Le Chat is now Vibe. Where Mistral's open-weight models and EU hosting beat ChatGPT, and where ChatGPT's wider feature set still wins.

October 5, 2026
OpenAI Codex: What It Is and How to Get Started
What OpenAI Codex is, the four ways to run it, how sign-in works, what its approval and sandbox modes mean, and how AGENTS.md steers it.

October 5, 2026
OpenCode vs Claude Code: Open Source or First-Party?
OpenCode is an MIT-licensed agent that works with many model providers. Claude Code is Anthropic's own harness for Claude. What each trade costs you.

October 5, 2026
What Is an API Key? A Plain-English Guide
An API key is a secret string that lets software use an AI service on your account. How it differs from a password, where to get one, and how to keep it safe.

October 5, 2026
What Is RAG? Retrieval-Augmented Generation Explained
What is RAG? Retrieval-augmented generation lets an AI look up your documents before it answers. How it works, RAG vs fine-tuning, and where it breaks.

October 2, 2026
Cursor vs Codex: Editor First or Agent First
Cursor is an AI editor that grew agents. Codex is an agent that plugs into your editor. They now overlap a lot; here is what still separates them.

October 2, 2026
Lovable vs Cursor: Who Owns Your App's Stack
Lovable hosts your app and runs its backend. Cursor edits a repo and hosts nothing. How to choose, and how the Lovable-to-Cursor handoff really works.

October 2, 2026
OpenAI Codex Alternatives: Pick the Part You're Replacing
Codex is a CLI, an IDE extension, cloud tasks and an app. The right alternative depends on which part you're leaving: terminal, editor or async agent.

October 2, 2026
Replit vs Bolt: Where Your App Lives, and What Leaving Costs
Replit runs your app in a full cloud workspace; Bolt runs a JavaScript project in your browser. Here's how that changes hosting, data, auth and the exit.

October 2, 2026
UiPath Alternatives: Match the Tool to the Job Your Bots Do
The right UiPath alternative depends on what your bots do: drive screens, call APIs, or orchestrate processes. Options for each, open source included.

October 2, 2026
UiPath vs Power Automate: Where Your Bots Live
Power Automate runs inside your Microsoft tenant. UiPath is a platform of its own. How that shapes robots, governance, licensing and AI agents.

October 2, 2026
Windsurf vs GitHub Copilot: Editor-First vs GitHub-First
Windsurf is now Devin Desktop, an agent-first editor. Copilot lives in your existing editor and on GitHub. Here's how to choose between them in 2026.

October 2, 2026
Zapier vs IFTTT: Which One Fits Your Automations?
IFTTT meters how many applets you keep; Zapier meters how many actions run. Here's which one fits smart home, phone and business workflows.

October 1, 2026
Bubble Alternatives: Ranked by What You Can Export
Bubble apps can't leave Bubble. Compare WeWeb, FlutterFlow, Webflow, Adalo, Glide, Softr and more on code export, mobile, and backend.
