These are real projects — tools I use, systems I depend on, writing I'm doing. AI is a core part of the workflow for each of them, not a bolt-on.
SaveWisdom is a daily reflection coach that runs entirely through Telegram. Every morning it sends one prompt — a question, an observation, a challenge — designed to surface something worth thinking about.
The prompts are grounded in stoic philosophy and modern behavior change research. Claude generates them. Hermes (my Telegram gateway agent) delivers them. I respond when I want to, ignore them when I don't, and the system doesn't nag.
It started as a weekend experiment to see if I'd actually engage with a daily reflection practice if it came to me instead of requiring me to go somewhere. I do. It's one of the stickiest things I've built.
Frictionless delivery (Telegram, no app). One prompt, not five. No response required. The habit loops around receiving, not producing.
A book-in-progress about navigating hard life transitions — the moment when more stops feeling like the answer, and you have to figure out what "enough" actually means.
The process: Grok designed a daily story prompt system. Hermes delivers one prompt per day via Telegram. I respond in my own voice, stream of consciousness. The system captures and stores the raw material. Editing and structure come later.
Phase 1 is raw capture only — no editing, no structure, just get the stories out. This keeps me from getting stuck in craft before I have material.
Grok designed the prompt arc. Hermes manages the delivery schedule and stores responses. I show up and write. The agents do the logistics so I can focus on the actual hard part — telling the truth.
agent-brain is the shared coordination repo for the whole AI agent system. It's a git repo that all four agents (Hermes, Grok, Claude Code, Codex) read and write — the shared working memory.
The core mechanism is handoffs: structured files that route work between agents. Grok writes a handoff to Claude Code. Claude Code implements, then creates a completion handoff back to Grok. A watcher script monitors the repo and auto-dispatches agents when handoffs appear.
The chain registry tracks the full delegation graph — who dispatched what, to whom, and whether it closed. This site's interactive visualizer shows those chains.
A systematic options income system built around the Wheel strategy — selling cash-secured puts on quality equities, taking assignment, then selling covered calls until the position exits. Each cycle is defined by written rules. No discretion on entries or exits.
The trend-trading stacks (swing, day, multi-timeframe) were shelved after backtesting: post-cost returns showed no reliable edge over buy-and-hold. ADR 0006 documents the decision. The Wheel survives the same test — premium income is the return, not price prediction.
Hermes sends entry signals and cycle updates via Telegram. The rules live in architecture decision records in the repo. Paper trading first — a verifiable track record before real money moves.
The system's job is to remove discretion. Backtest the rules, paper-trade the rules, then follow the rules — the agents handle scanning and notification so the human only handles judgment calls the rules don't cover.
40 triangles, each driven by a tiny neural network. A genetic algorithm runs every generation — top 30% breed, losers fade and die. No API cost: trains from random weights in your browser. Click to place food, hit 20× to skip ahead.
Python pipeline that reads tax documents (1099s, W-2s, brokerage statements) and auto-fills a 1040 workbook. Built in a weekend — saved a few hours the first year it ran. Needs polish but works.
Personal utility scripts and automation helpers. The scaffolding is there. Actual utilities get added as I encounter recurring friction — rather than pre-building things I might not need.