Bitcoin
I save in Bitcoin. This is where I explain why and collect the resources I would share with someone curious. — Why I save in Bitcoin
Back to Home
daily
daily
daily
occasional
occasional
experimenting
occasional
daily
daily
daily
daily
occasional
daily
daily
experimenting
experimenting
daily
daily
daily
occasional
daily
daily
daily
daily
daily
daily
Notes
What I’m using, learning, and spending time on. AI tools, Bitcoin, my church, and the projects I’m building. I update this page when something changes.
Updated
Away from the keyboard
Faith, Bitcoin, and the things I keep coming back to.
Truth Chapel
My church. Livestreams and teaching are available on YouTube. — Watch Truth Chapel
Models
The raw horsepower. Opus 5.5, GPT-6.1 Sol, and Grok 4.7 carry the daily work; the rest come in when a job calls for them. The one local model, Qwen3.8-27B, runs at Q4_K_M quantization through llama.cpp.
Claude Opus 5.5
dailyanthropic · model · default
My default. The model behind most of my Claude Code sessions — planning, larger edits, and the long, context-heavy, repo-shaped work.
+ Strong at planning and long sessions
+ Tight, deterministic output on routine edits
GPT-6.1 Sol
dailyopenai · model · second opinion
My daily OpenAI model through Codex, and my go-to second read — a different angle when Claude and I keep circling the same answer.
+ Useful contrast to the Anthropic models
+ Good at reading a repo cold
Grok 4.7
dailyxai · model · grok build
xAI’s current model, run through Grok Build and covered by my X Subscription. A third daily read next to Claude and GPT.
+ A third independent read in the daily rotation
Claude Fable 5.1
occasionalanthropic · model
Anthropic’s top model. I bring it in when a problem is niche or hard enough to be worth it; Opus handles the rest.
+ Careful on niche, hard problems
GPT-6 Astra
occasionalopenai · model
OpenAI’s flagship, saved for the jobs where Sol comes up short.
+ The heavier OpenAI option when Sol is not enough
Qwen3.8-27B
experimentingqwen · model · llama.cpp · local
The only local model I still run. Qwen3.8-27B at Q4_K_M quantization, served by llama.cpp on the 3090.
+ Private and local
Muse Wonder
occasionalmeta · model · opencode
Meta’s model, run through OpenCode. It is not a frontier coding model, but it is better than that sounds — I like how it has worked and how it responds, so it stays in the rotation for occasional use.
+ Better than its tier suggests on real work
+ A response style I keep coming back to
Harnesses
The agent loop itself — the thing that takes a model, gives it tools, and lets it inspect a repo, edit, and run checks. Claude Code, Codex, and Grok Build each run their own vendor’s models; OpenCode and Cursor cover the others — OpenCode locally, Cursor as cloud agents I reach through Grok Bot. The interface I drive a harness from is a separate choice.
Claude Code
dailyanthropic · cli · coding agent
My default harness for high-context, repo-shaped work — planning, larger edits, and longer sessions where keeping the whole repo in view matters. Runs the Claude models; I drive it from T3 Code.
+ Strong at planning and repo-shaped work
+ Holds context across longer sessions
- I still pair it with Codex when I want a second read
Codex
dailyopenai · cli · coding agent
My implementation-and-inspection agent: fast at reading the repo, making focused edits, and running the test/check loop. I drive it through T3 Code, often as a second read against Claude Code.
+ Quick into implementation and repo inspection
+ Clean inside T3 Code
- I reach for Claude Code first on the largest, most context-heavy tasks
Grok Build
dailyxai · cli · coding agent
xAI’s coding agent, and the newest vendor harness in my rotation. It runs Grok 4.7 through the same inspect, edit, and check loop as the others, and comes with my X Subscription.
+ Grok models in a real repo loop
+ Included with the X Subscription
- Newest vendor harness — still learning where it beats the others
OpenCode
dailyopen source · cli · coding agent
The open-source harness, and the one I run Muse Wonder through. It is also how the local model fits the loop: OpenCode talks to llama.cpp on the RTX 3090 PC, which serves Qwen3.8-27B at Q4_K_M quantization, so the same inspect, edit, and check workflow runs against a model on my own hardware.
+ Vendor-neutral — cloud and local models in the same loop
+ Runs the 3090’s Qwen3.8-27B through llama.cpp
- One more harness to keep configured next to the vendor CLIs
Cursor
occasionalcursor · cloud agents · coding agent
Cursor’s cloud agents, not the editor. I rarely sit in Cursor itself; I dispatch its agents through Grok Bot, which makes Grok Bot the interface and Cursor the harness running the repo loop in the cloud. It comes with the X Subscription.
+ Cloud agents keep working without my machine in the loop
+ Reached through Grok Bot instead of another app to sit in
- Occasional by design — the local harnesses carry the daily work
Interfaces
The surfaces I sit in front of.
T3 Code
dailyinterface · multi-harness · daily driver
Where I spend most of my time now. Not a harness — it sits on top of Claude Code, Codex, Grok Build, and OpenCode and lets me run any of them from one window, with my models pinned to keyboard shortcuts so switching is a keystroke instead of a context rebuild. Cursor’s cloud agents are the exception: those I reach through Grok Bot instead.
+ One interface over four harnesses
+ Switch models and harnesses without leaving the flow
Grok Bot
dailyspacexsi · personal agent · app
SpaceXSI’s personal agent, and one of the two apps I actually work in, with T3 Code. It runs on its own cloud computer, signs into apps the way I would, and keeps working with my laptop closed. It is also how I reach Cursor’s cloud agents, so it is the interface even when Cursor is the harness doing the work. It comes with my X Subscription.
+ Keeps working without my machine on
+ Dispatches Cursor cloud agents
Evaluating
Tools I am testing against my real workflow before promoting them to daily-driver status.
Muse
experimentingmeta · personal agent
Meta’s personal agent. I am testing it next to Grok Bot.
+ A second personal agent to compare against Grok Bot
- Too new to have an opinion yet
Hermes Agent
experimentingnous research · orchestration · command center
Nous Research’s agent harness, self-hosted on my home StartOS box. It takes work over a private Discord server and can kick off T3 Code sessions on my Mac over Tailscale. For me it is an async lane I can reach from my phone while most real work still happens locally.
+ Remote control from my phone via Discord
+ Private by default — no public exposure
- Still deciding what actually belongs in a remote lane versus Grok Bot and the local loop
Subscriptions
The paid plans that make the stack work — a different kind of thing from the agents and models they unlock.
The X Subscription
dailyspacexsi · Super tier · $100/mo
- X
- Grok
- Cursor
- Grok Bot
SpaceXSI’s bundle of Grok, Cursor, and X Premium, on the Super tier at $100/mo. I am a heavy Grok Bot and Grok user, with occasional Cursor use on the same plan.
+ One plan covers Grok, Grok Bot, Cursor, and X
+ Replaces what used to be three separate subscriptions
Claude Max
dailyanthropic · $100 plan
The plan behind my Claude Code and T3 Code usage — enough headroom for the heavier, repo-shaped sessions.
+ Room for longer Claude Code runs
ChatGPT Pro
dailyopenai · $100 plan
The plan behind my Codex work and the GPT-6 models.
+ Makes Codex a real daily agent instead of an occasional backup
Infrastructure
Where the work and the sites actually live — the Mac, the home GPU PC, the always-on VPS, hosting, and DNS.
M1 MacBook Pro
dailyapple silicon · local environment · hardware
Where the work actually happens. Not an AI tool, but the machine the harnesses edit on and the checks run against, and the default over the VPS for nearly everything. Still plenty of headroom for the whole stack of CLIs, editors, and a browser at once.
+ Handles the full local toolchain comfortably
+ Quiet, cool, and always ready
- Local model inference runs on the 3090 PC instead
RTX 3090 PC
occasionalnvidia · 24 GB VRAM · llama.cpp · hardware
My Windows desktop with a 24 GB RTX 3090. It runs llama.cpp serving Qwen3.8-27B at Q4_K_M quantization over Tailscale so the Mac can use the local model without giving up laptop memory.
+ 24 GB of VRAM handles 30B open-weight models comfortably
+ Shared with the Mac over Tailscale
- Only on when I need local inference or gaming
Hostinger VPS
dailyhostinger · KVM 4 · Ubuntu 24.04
My always-on Linux box — a Hostinger KVM 4 on Ubuntu 24.04. Workers handle all of my public web apps, so this server has one job: an always-on T3 Code host I can reach from anywhere through T3 Connect or Grok Bot, plus a Tailscale exit node. No public web ports are open; SSH only listens on Tailscale. — my referral
+ Always-on T3 Code host when my Mac is closed
+ SSH over Tailscale only — no public ports open
+ Doubles as a Tailscale exit node with automated daily backups
- I own the patching, backups, and uptime myself
Cloudflare Workers
dailyhosting · next.js · opennext · edge
Where my public sites live, including this one and morningportion.com. Next.js apps ship through the OpenNext adapter, so the same App Router codebase runs at the edge instead of on a Node server. Static things skip the framework entirely and deploy as plain assets. Moving here from Vercel put hosting, DNS, storage, and access control on one bill and one dashboard.
+ One platform for hosting, DNS, KV, R2, and access control
+ OpenNext runs a normal Next.js codebase at the edge with no rewrite
+ Static sites deploy as assets with no framework overhead
- The Workers runtime is not Node, so some npm packages need a compatibility flag or a swap
Cloudflare Access
dailyzero-trust · auth · sso
How my private apps stay private without building auth. A one-time-code login sits in front of the whole origin, so tools like my workout logger and a few family apps are reachable from any device but open to nobody else. It is the reason those projects can be genuinely useful to me and still never expose a login form to the internet.
+ Real access control on a personal project without writing an auth system
+ One-time email codes mean no password to manage
+ Applies to the origin, so nothing leaks if a route is forgotten
- Anything behind it cannot be shown off without a separate sanitized build
Cloudflare DNS and Registrar
dailydns · domains · registrar
My DNS and domain registrar — the layer that points every domain at Workers, the VPS, and everything else. At-cost domain pricing and fast DNS make it the quiet foundation under the whole stack.
+ At-cost domain registration with no markup
+ Fast, reliable DNS for every property
+ Single place to manage all my domains
Tools
Companion utilities and helper surfaces that support my workflow.
Superwhisper
dailyvoice · dictation · macOS
Push-to-talk dictation surface. Hold the hotkey, talk, release — audio is transcribed then processed by a model of my choice, including local models. — superwhisper.com
+ Push-to-talk hotkey makes voice feel like a real input mode
+ Choose transcription and processing models independently, including local models
+ Modes for verbose dictation, summarized meeting notes, and clean prose
- Mode customization takes a beat to internalize when you build out more than a couple
Tailscale
dailyvpn · network
Zero-config mesh VPN that keeps my machines and VPS reachable securely.
+ Simple secure networking across devices
+ Works well for remote agent access