My Complete AI Toolbox: Find the Tool for Whatever You Want to Do

I was recently preparing an introductory AI lecture for our therapist colleagues, and thought I’d put together an advanced list of all the tools I normally use and the programs I’ve written. This way, when you want to do something, you can quickly look up “who to go to for this function.” It’s also something I’ve always wanted to organize for myself, so I’m taking this chance to write it all out.

This post doesn’t pick an audience and leaves nothing out. I’m listing everything from AI assistants down to my home backup system. To use it, first find the category for your need, then look at the table in that section. The ones marked ⭐ are programs I wrote myself and have open-sourced; feel free to just take them. The ones marked “Free” are those I actually use within their free tiers. (I love free stuff too much, I pay for almost none of this XD)

Table of Contents

• 1. Main AI and Engines — AI Assistants and Main Collaborators・Free Cloud and Local AI Engines
• 2. Audio and Document Processing — Speech-to-Text・Text-to-Speech・OCR
• 3. Learning and Knowledge Management — Notes and Personal Knowledge Base・Papers and Clinical Evidence・Exam Practice
• 4. Publishing: Websites and Email — Website Hosting and Cloudflare・Custom Domain Email and Sending
• 5. Automation and Self-Hosted Backbone — Automation, Scheduled Jobs and Notifications・Home Server and Smart Home・Backups and UPS
• How to Start?

1. Main AI and Engines

AI Assistants and Main Collaborators

Claude Code is one of the few things on this list I pay for, and pay for gladly. It’s not just chat; I built this blog and almost all the tools below with it. I use other AIs for second opinions: Gemini for research, Codex for nitpicking. Note that data on Gemini’s free tier is used for training, so don’t feed it sensitive content. For Codex, remember to go to settings and turn off training.

Once my workload got bigger, herdr let me run several Claude Code tasks in parallel: transcribing a lecture over here, organizing notes over there, without interfering with each other. Running multiple tasks for a long time, I found the most common cause of death wasn’t code errors, it was getting decapitated by usage limits. So I made claude-pacer: there’s a fuel gauge in the status bar to see how much quota is left. When it’s running low, the AI will wrap up its current work, save it, and automatically resume when the quota resets. The full story is in this post.

Mindset

Pick one main tool and use it deeply; use the rest as second opinions. Bouncing around between tools won’t build a workflow.

Free Cloud and Local AI Engines

When writing automation scripts, a lot of the “grunt work” (categorizing, extracting keywords, translating) doesn’t need the smartest models. The free tiers from these providers are enough:

My division of labor: high-value work requiring judgment goes to Claude; massive amounts of mechanical grunt work go to free APIs; sensitive data always stays on local models.

2. Audio and Document Processing

My main use case is turning lecture and class recordings into transcripts and then organizing them into notes, so this is where I’ve invested the most.

Speech-to-Text

I fell into a trap while picking an engine: online leaderboards are tested on “other people’s data,” which might be completely irrelevant to your use case. So I wrote asr-benchmark: build a glossary from literature in your field, and measure how many “real terms each engine catches, and how many non-existent terms it hallucinates.” In my medical lecture scenarios, Breeze-ASR-25 caught specialized terms at a significantly higher rate than vanilla Whisper, so I made it my default. The full method is in this post: My Data, My Benchmark.

Text-to-Speech

I use BreezyVoice to pre-generate my home voice announcements: the morning briefing and the laundry completion reminder are all in its voice, routed through Category 5’s Home Assistant to play out loud.

OCR and Document Processing

Note

General-purpose AIs (the kind where you tell ChatGPT “read this image for me”) will skip words when doing verbatim OCR. They confidently skip parts they can’t see clearly. For official documents, please use a dedicated OCR engine.

3. Learning and Knowledge Management

Notes and Personal Knowledge Base

vault-search runs entirely locally, notes never leave your machine, and the AI can directly query your notes vault (the original story is in this post). textbook-to-note was my core tool for preparing for the board examination; I just open-sourced it recently: intro post here.

Papers and Clinical Evidence

I wrote the first three myself. They link up perfectly into a “discover → download → read” assembly line, and they are also my most used series on GitHub:

The Paper Trilogy has an intro post for each: paper-radar, paper-fetch, and paper-review-and-digest.

OpenEvidence is handy, but the citations the AI provides must be verified, so I wrote the verification process into a tool too (oe-verify inside openevidence-tools): it fetches the original text for every single citation and compares them, directly flagging any mistakes.

Exam Practice

Those preparing for the national medical licensing exam or the board examination can self-host a copy; the introduction is in this post.

4. Publishing: Websites and Email

This blog, along with a few small sites I’ve made (Rehab Course Radar, etc.), are all hosted on free services. My only monthly cost is the domain fee. The Cloudflare ecosystem is the core:

Website Hosting and Cloudflare

These two Zero Trust tools are worth singling out: Tunnel lets me safely connect back to services running at home (analytics, push notifications, photo library) from the outside; Access lets me lock down sites I’m not ready to make public (my paper radar, personal dashboard) so only I can log in. Both are free, and they’re godspends for self-hosted tinkerers.

Custom Domain Email and Sending

If you want to send and receive emails as yourname@yourdomain, it’s actually completely free:

For the Gmail MCP, I use the open-source version and add my own key encryption for protection. Once hooked into Claude Code, things like “find me that registration confirmation email from last month” can be solved with a single sentence.

5. Automation and Self-Hosted Backbone

Automation, Scheduled Jobs and Notifications

Course registrations opening, paper updates, server anomalies, typhoon work/class cancellations—they all follow the same pattern: “a scheduled job on Oracle checks it → if there’s a change, ntfy pushes it to my phone.” I write it once and use it forever.

Home Server and Smart Home

The self-hosted track is my hobby, and it’s also the foundation for many of the services above:

Home Assistant is worth a special mention: it’s connected to my AI tool workflow. The morning briefing uses BreezyVoice’s synthesized voice to announce today’s schedule, and when the washing machine is done, it yells at me in Chinese to go hang the laundry 🤣. Immich is the solution for “finding photos”: I can find a photo just by describing it in a sentence, and facial recognition automatically groups people, without ever handing my photos over to the cloud.

Backups and UPS

The more you play with self-hosted stuff, the more seriously you have to treat “what happens when it breaks.” I configure things according to the 3-2-1 rule (three copies of data, two different media, one off-site):

Off-site backup uses WireGuard to connect the NAS units in my Hualien and Tainan homes into an encrypted tunnel, syncing automatically every night. The UPS actually came in handy on the eve of a typhoon; the real-world test log of that time is in this post.

How to Start?

It’s a long list, but don’t start with the tools, start with your pain points. Think about the one thing you do repeatedly every week that takes the most time, go back to the corresponding category, and ignore the rest for now.

My own sequence grew organically like this too: first it was study notes (textbook-to-note), then papers (The Paper Trilogy), and only then did the websites, automation, and this whole home setup slowly grow out of it. Every tool is here because it solved a real problem at the time; that’s why they stayed.

If you have any questions, feel free to leave a comment or email me, and you’re also welcome to just open a GitHub issue~

Buy me a boba!