My AI Tools

Last updated: March 24, 2026

AI is in everything I do now. Not in a hype-cycle, throw-it-at-the-wall way. More like “this changed how I build things and I’m not going back.”

I code with it, write with it, transcribe with it, and I’ve built an agentic assistant that runs on a Mac Mini under my stairs.

Here’s what I actually use every day, and what turned out to be a waste of time.

Coding & Automation: Claude Code

Claude Code overview - Claude Code Docs

Claude Code is an agentic coding tool that reads your codebase, edits files, runs commands, and integrates with your development tools. Available in your terminal, IDE, desktop app, and browser.

Claude Code Docs

Claude Code is how I build almost everything now. It’s Anthropic’s CLI tool for coding with Claude, and I’ve shipped more projects in the last few months than I did in the previous two years.

Here’s the setup that makes it work: Claude Code runs on a headless Beelink box sitting next to my OpenClaw Mac mini (under my stairs). I SSH in from my MacBook Air, using Ghostty, and use tmux to manage multiple projects at the same time, and if a build is going to take a while, I just close the laptop and walk away. Claude Code keeps running.

That last part is the key. I can kick off a long coding task, go make dinner, come back, and it’s done. No IDE to keep open, no browser tab to babysit.

Syncthing

I use Syncthing to keep a shared folder between the laptop and the Beelink, so passing screenshots and files back and forth is seamless.

Projects I’ve built entirely (or nearly entirely) with Claude Code:

• This Ghost theme you’re looking at right now
• My YouTube upload workflow
• LickityClick (a custom link shortening SaaS that is powering my affiliate links)
• A hub for my premium members
• An SEO toolkit to keep tabs on this site and send me regular email reports.
• Server automation scripts to email me about server health, backup issues, etc.
• A sponsor response workflow, to help me manage inbound email.

Claude Code is easily the most impactful tool I’ve picked up in years.

Automation: n8n

n8n is my self-hosted automation platform. I don’t use AI inside n8n directly — it’s all node-based workflows that connect services together. What makes it part of my AI stack is that Claude Code builds and manages the workflows for me. Form submissions that create Ghost members, newsletter signups, webhook routing — I describe what I need, and Claude Code calls the n8n API to build the workflow. These days, I hardly ever open up the n8n interface and do anything by hand.

The Terminal: Ghostty

Ghostty

Ghostty is a fast, feature-rich, and cross-platform terminal emulator that uses platform-native UI and GPU acceleration.

Ghostty

Ghostty is the terminal I run everything through. I switched from iTerm2 after hitting bugs with Claude Code and running into iTerm's scrollback limit. Ghostty is fast, handles long sessions without choking, and stays out of the way. Claude Code lives inside it.

Code Editor: Antigravity

Antigravity is the code editor I reach for when I need one. It’s Google’s cloud IDE, bundled with the Gemini Ultra subscription. It handles visual diffs, browsing large codebases, and anything that benefits from a GUI — though honestly, Claude Code handles most of what I’d open an editor for.

I’m also watching OpenCode, which is an open-source alternative to Claude Code. I plan to migrate some of my workflows there eventually, especially once I upgrade to a more powerful Mac Studio. But I’ve invested so much in Claude Code configs and workflows that the migration needs dedicated time.

Markdown: iA Writer

iA Writer is how I read and edit Markdown files without opening a full IDE. Claude Code, Gemini CLI, and Antigravity all generate Markdown that I want to review on the go. iA Writer lets me open those files quickly without adding them to my Obsidian vault. Turn on preview mode with the button in the upper right corner for a more human reading experience — if your eyes have grown tired of reading hashtags and stars.

Desktop AI: Claude Desktop

Download Claude | Claude

Download Claude for desktop and mobile. Access AI assistance natively on Mac, Windows, iOS, and Android across all your devices.

Claude

Claude Desktop is kind of a legacy app at this point, now that Claude Code handles all my coding. But I still open it constantly for one reason: history.

I’ve used Claude Desktop so much that its project memory and conversation history give me weirdly relevant answers. It knows my stack, my preferences, my past decisions. When I need a quick answer about something I’ve worked on before, it just has all that context.

The other thing it does well is screenshot pasting. When Claude Code is running on a remote box, getting screenshots into it takes a few extra steps. With Claude Desktop, I just paste and go.

I also use Claude on my phone, but the voice mode leaves a lot to be desired. It’s not hands-free, which defeats most of the purpose. Grok on the iPhone action button handles that job better right now.

Local AI: LM Studio, Ollama & OpenClaw

LM Studio - Local AI on your computer

Run local AI models like gpt-oss, Llama, Gemma, Qwen, and DeepSeek privately on your computer.

LM Studio

I run local models too, though they’re more experimental than daily drivers.

LM Studio is where I test and run open models locally. The killer feature is LM Link, which lets me serve models from my Mac Studio to my laptop over the network. When the Studio isn’t being used for video editing, it becomes a local inference server.

Ollama is the other local model runner I've use. I’m currently investigating its Anthropic API compatibility mode for potential video content. LM Studio is my daily use right now, but I may go back to Ollama if the new Mac Studios and local LLMs pan out as expected.

Then there���s OpenClaw, which is the project I’m very excited about. It’s a custom agentic AI assistant running on an M1 Mac Mini tucked under the stairs in my basement. It has its own memory system, connects to Obsidian, and I’ve made multiple videos about building it.

AI Subscriptions: Gemini Ultra & Grok

I pay $250/month for Google Gemini Ultra. Yes, $250. But here’s what you actually get for that: high rate limits to Gemini models, the Antigravity IDE, Google’s image generation tools, and Veo for AI video generation. I use Veo to generate b-roll clips for YouTube videos, and it saves more production time than you’d expect.

The first year also includes $100/month in API credits, which I burn through on speech dictation cleanup, programmatic image generation, and API credits for OpenClaw. You also get 30TB of Google Drive storage and YouTube Premium.

The catch here, is you have to sign up for Ultra with your personal account or you don't get the storage, API credits, or YT Premium. Lame.

I also have X Premium, which includes Super Grok. Grok’s best feature isn’t on desktop though. It’s in my Tesla. Voice-activated Grok in the car handles navigation questions, answers the kids’ random questions on family drives, and honestly just makes for good conversation. I also mapped Grok to the iPhone action button for quick voice answers when I’m away from a screen.

Oh, and X Premium is how I got the @daveswift handle. Follow me there if you don’t already.

Transcription: MacWhisper

🎙️ MacWhisper

MacWhisperQuickly and easily transcribe audio files into text with OpenAI’s state-of-the-art transcription technology Whisper as well as Nvidia Parakeet. Whether you’re recording a meeting, lecture, or other important audio, MacWhisper quickly and accurately transcribes your audio files into text.📲 MacWhisper is now also available on iPhone and iPad, download it here.🎁 Get 5 euros off in January by clicking this link.Full Feature List Easily record and transcribe audio files on your Mac Full text and speaker search through all your transcripts System wide dictation with Whisper to replace Apple’s own dictation, even with the best Whisper models Just drag and drop audio files to get a high quality transcription Automatically record meetings in Zoom, Teams, Webex, Skype, Chime, Discord and more. Record directly from your microphone or any other input device on your Mac All transcription is done on your device, no data leaves your machine. This makes MacWhisper a great app for sensitive audio such as interviews. Save or export your transcripts as a .whisper file, which includes the original audio and all your transcription edits for easy sharing .srt & .vtt subtitles export as well as csv, dote, docx, pdf, markdown and html exports Metal and GPU support for extremely fast transcription Get accurate text transcriptions in seconds (up to ~30x realtime) Search the entire transcript and highlight words Audio playback synced to transcripts Supports 100 different languages Copy the entire transcript or individual sections Star/Favorite segments Compact mode (hide timestamps) Automatically remove ums, uhhs and other similar filler words Drag and drop directly from Voice Memos Edit and delete segments from the transcript Add up to two speakers manually Inline Video Player Video playback synced to subtitles View multiple language subtitles at once in the videoplayer Select transcription language (or use auto detect) Change playback speed from 0.5 to 3.0x (audio & video) Supported formats: mp3, wav, m4a, ogg, opus, mov and mp4 videos. Adjust whisper settings (beam search / greedy, beam size etc) Supports all Whisper models, some models are only fully available for Pro users ⭐️ MacWhisper Pro All above features Support for Parakeet v2 (for up to 300x realtime transcription at the highest accuracy) on m-series Macs Automatic Speaker Recognition with local models (M-series Macs only) and with ElevenLabs and Deepgram Automatic spelling, punctuation and grammar improvement in dictation mode (requires AI Service to be setup) Batch Transcribe as many files one after the other. Useful if you want to add subtitles to an entire season of a show, or if you have a lot of interviews to go through Support for WhisperKit and Distilled models Integrations with Notion, Make.com, n8n, Zapier, custom webhooks and Obsidian to automatically forward your transcripts Transcribe YouTube videos Realtime captions / subtitles with live translation. Can be used with the microphone or system audio. Watch Folder support to automatically transcribe files when they are added to a directory of your choice. The files can automatically be transcribed into a variety of formats. Support for OpenAI (ChatGPT), Anthropic (Claude), Groq, Ollama, XAi, Deepseek, Custom OpenAI API endpoints and Azure AI models for easy prompting Support Cloud Transcriptions through OpenAI, ElevenLabs, Deepgram, Groq and custom Whisper servers Manually add speakers to your transcript for a cleaner export Menubar app for accessing Whisper anywhere from your Mac Global, access MacWhisper from anywhere in a spotlight type view for instant transcription and easy pasting into other apps ChatGPT integration (with your own API key) Ignore segments such as [SILENCE] from appearing in your transcripts Supports GPT4, GPT4 Turbo, GPT4o and GPT4o-mini as well as older models Anthropic Claude Integration (with your own API key) Record and transcribe system audio (to record meetings for example) Supports Tiny (English Only), Tiny, Base, Small, Medium and Large (V2 and V3) models Add your own custom GGML models Change the starting timestamp for the transcript Translate audio file into another language through Whisper (use the Medium or Large models, the results will not be perfect and I’m working on more advanced ways to do this) Translate the full transcript by adding your own (free) DeepL API key. Translate subtitles into different languages Inline and separate video player with subtitle and multiple translated subtitles support Transcribe podcasts by combining single track audio for each host (beta) One time payment, no subscription. Pay once and use forever. Higher priority support. I’ll try to email you back as soon as possible if you run into anything. If you’re a journalist, student or non-profit, send me an email at support@macwhisper.com and tell me about your work to get 25% off 🙂 If you purchase MacWhisper Pro and are not happy with it, let me know within 7 days what could be improved and I’ll refund you. Support for OpenRouter Support for ElevenLabs Scribe and Deepgram Nova After downloading MacWhisper you will have to fill in your license key to unlock all Pro features.If you want to purchase more than 20 licenses, or if you’re looking for an MDM deployment or something custom, please send an email to support@macwhisper.com or check out the MDM Documentation.100+ Supported LanguagesMacWhisper can transcribe audio in the following languages:English, Chinese, German, Spanish, Russian, Korean, French, Japanese, Portuguese, Turkish, Polish, Catalan, Dutch, Arabic, Swedish, Italian, Indonesian, Hindi, Finnish, Vietnamese, Hebrew, Ukrainian, Greek, Malay, Czech, Romanian, Danish, Hungarian, Tamil, Norwegian, Thai, Urdu, Croatian, Bulgarian, Lithuanian, Latin, Maori, Malayalam, Welsh, Slovak, Telugu, Persian, Latvian, Bengali, Serbian, Azerbaijani, Slovenian, Kannada, Estonian, Macedonian, Breton, Basque, Icelandic, Armenian, Nepali, Mongolian, Bosnian, Kazakh, Albanian, Swahili, Galician, Marathi, Punjabi, Sinhala, Khmer, Shona, Yoruba, Somali, Afrikaans, Occitan, Georgian, Belarusian, Tajik, Sindhi, Gujarati, Amharic, Yiddish, Lao, Uzbek, Faroese, Haitian Creole, Pashto, Turkmen, Nynorsk, Maltese, Sanskrit, Luxembourgish, Myanmar, Tibetan, Tagalog, Malagasy, Assamese, Tatar, Hawaiian, Lingala, Hausa, Bashkir, Javanese, Sundanese.System RequirementsMacWhisper requires a lot of computer memory to work well. To use the Medium and Large models your Mac should have more than 8GB of RAM. Performance on older Intel based Macs can also be bad but I have not been able to test this properly.Privacy Policy and Terms of UseReviews👨‍💻 Check out my other macOS utilities:OpenAI Bundle - Get all my OpenAI apps at a discounted rateMacGPT - Use ChatGPT on your Mac and from your menubarDetective - GPT Vision for macOSVoices - High Quality Text to Speech with OpenAIText Assistant - Generate useful text and manage your prompts with GPT and your own OpenAPI keyVivid - Double the brightness of your MacBook Pro by always using HDR modeForehead - Hide the Notch and round your MacBook cornersCooldown - Quickly toggle Low Power Mode from your menubarSpeedy - Fast Speedtest in your menubarPippo - Improve the Picture-in-Picture video player with seek controlsWhisper was made by building on top of all the hard work from Georgi Gerganov, check out his Whisper implementation here: https://github.com/ggerganov/whisper.cpp

MacWhisper might be the most underrated app I own. It started as my transcription tool, and I used it to transcribe over 500 YouTube videos. But the reason I can’t live without it now is dictation.

Typing all day makes my wrists ache. I don't have a full blown condition or anything, but MacWhisper lets me dictate long-form text and get clean transcriptions back almost instantly. It runs locally using Whisper models, so nothing leaves my machine.

I’ve since moved my YouTube transcription pipeline to a Claude Code workflow that runs transcription models locally, but MacWhisper is still my go-to for day-to-day dictation and transcribing YouTube videos where I just want the highlights.

What I'd love to see – a great iPhone Transcription experience. iPhone transcription is bad across every app I’ve tried. I really hope Apple upgrades their built in system to Whisper or Parakeet-level models, because the on-device transcription right now just isn’t there.

What Didn’t Work: Notion Mail

Notion Mail

Personalized to your work and beautifully designed—Notion Mail is the only inbox that makes life simpler.

Notion

Not everything sticks. I used Notion Mail for about six months. The concept was great: AI-powered email triage that automatically categorized and prioritized everything.

When it worked, it was fantastic. When it didn’t, it was a mess. The AI would just go down with no warning, and there was no way to revise AI-generated responses before sending. You can’t have that when you’re emailing clients and sponsors.

Notion Mail also required switching from my self-hosted email to Google Workspace. That part actually turned out fine (I got Google Drive and Gemini Pro out of it), but the mail experience itself wasn’t worth it.

I’m now building my own AI email triage and response system with Claude Code, and I’m testing Mimestream as a native Gmail client on the Mac. I was a beta user years ago, so it’s a bit of a homecoming. It was free then, I'm not sure I'm willing to pay $50/year for it.

That’s my AI stack right now, it changes quickly. Some of these tools completely changed how I work. Others were expensive lessons in what not to depend on. If you’re just getting started with AI tools, grab Claude Code and MacWhisper. Everything else is optional.