Michelle Feng · San Francisco
Measuring myself against other people never worked — there’s always someone better, and knowing that never told me what to do next. So I keep the only score that produces action: find something I can’t do yet, do it, and watch how my thinking changes. I’ve run that loop for the past year as founding engineer at Iditor, shipping AI that remembers you across iOS, web, and a Chrome extension. This site is the rest of it — what I build for no one but myself. I don’t trust bios; actions are the honest description. Here they are.
Founding engineer at Iditor · Boston University CS ’25 · 4 published agent skills
2024 → now
Everything I build makes the same move: take messy lived signals — energy, habits, conversations, model behavior — and compress them into one clear next action. So far it has taken three forms.
Complete systems, owned end to end: an energy-translation platform (Django + Next.js) answering "given what I’ve already spent today, what is safe to do next?", research that moved real numbers — debiasing text-to-image generation from 29% to 44.5% female representation, RL work with 10× faster convergence — and EchoChat at Iditor: chat, multimodel inference, memory, and retrieval in a live product.
What this proves — I can own a system from database to interface and ship it live.
The same systems, rebuilt as agent behavior instead of screens: long-term memory and retrieval for a live AI product — benchmarked to 95.8% on LongMemEval — and openClaw, a personal agent defined by identity, memory, and heartbeat files that tracks growth while I work, no dashboard required.
What this proves — I design how agents remember, decide, and stay consistent — not just how apps look.
Whole platforms distilled into installable agent skills — Next Mode, Identity Votes, One-Shot Positioning, Smart People Prep — each one npx install away. The newest thread turns the same method onto the models themselves: a structured, evidence-first knowledge base of LLM behavior.
What this proves — I can find the smallest version of a big idea that people actually adopt.
Three forms in two years, each distilled from the last. The projects change; the move compounds.
Don’t take the page’s word for it. Install one of my published agent skills and judge the craft directly:
Prefer to browse? github.com/myfeng10 ↗ · or try the working prototypes live: Energy, Identity, the lottery.
A system I can’t make someone else understand isn’t finished. Most of my work is the interface between a complicated process and a person who needs to stay oriented inside it.
See the visualization archive →Big ideas earn adoption by shrinking. I turned a whole platform into four installable skills — and I’d rather ship the version people actually use than defend the version I planned.
See what I’ve been building →Numbers where they exist, artifacts where they don’t. Every claim on this page links to something you can open, read, or run.
See the install command →Nothing I build is wasted — each project becomes compost for the next form of the same idea. The archive below is that process, kept honest in public.
See the timeline →Daily practice
One source, one tiny task, one sentence — drawn fresh each day. Built to keep interview prep light and consistent.
Archive
Everything above is the compressed version. This is the uncompressed one — how each phase actually felt, what it taught me, and why it mattered. If the top of the page earned your attention, this part is for you.
Making inner systems legible
This period concentrates on memory, direction, energy, identity, and the question of how to turn lived patterns into surfaces I can actually use later.
Project · June
A set of installable agent skills that turn energy, identity, weekly review, and archive practices into reusable decision workflows.
The shift is from personal ideology to portable behavior: the agent can notice patterns, make decisions, and hand back one next move.
Project · March
This site became a project about preserving meaning across time, not just displaying outputs. The redesign started when I realized the old structure could describe me, but could not help me remember myself.
The site needs enough structure to preserve memory, but not so much structure that it produces fake completeness.
Project · March
A tiny walking experiment about direction, drift, and the strange gap between what the body thinks it is doing and what it actually does.
The original mood was curiosity, not fear. It should stay playful, sleek, and quietly strange.
Project · February
A working system for translating sleep and the structure of a day into guidance about what kind of work is still safe to do.
The real question underneath it is not “how productive am I?” but “what kind of thinking is safe now?”
Project · February
A system that reads recurring actions as identity votes, trying to make becoming legible before it hardens into a story I tell too late.
The interesting part is not the label itself. It is the accumulation of repeated behavior over time.
Project · February
The bridge project: one place to capture a day, read energy and identity together, and keep a running history instead of isolated analyses.
This is where multiple tools started wanting to become one ritual.
Thread · February
A running note system for tracking patterns, shifts, and growth in a way that stays close to actual life instead of polished summaries.
This is the record underneath the cleaner interfaces.
Threshold year
Graduation and startup life changed the pace, stakes, and texture of work. This is the environment that later archive projects grow out of.
Shift · May to December
A transition from school structure into startup velocity, with a corresponding shift in how work, time, and responsibility felt day to day.
This period is less about one artifact than about the environment that changed what kinds of projects became necessary.
Project · May to December
Full-stack work across chat systems, multimodel inference, memory, and retrieval, in the context of a live social AI product.
This is where product engineering, memory systems, and real user-facing constraints met each other.
Research, teaching, and explanation
Before the recent personal systems work, the same instinct was already present in research, teaching, and interactive explanations.
Thread · Across the year
Research, teaching, and explanation work kept reinforcing the same instinct: complicated systems matter more when someone else can actually follow them.
This thread explains why so many later projects turn invisible processes into readable surfaces.
Project · Across the year
Older competitive programming and visualization work that still shows a consistent preference for explaining structure through interaction.
These pieces are earlier, but they still belong because they show a stable way of thinking.
I’m not looking for everyone — I’m looking for the people who read this far and recognized something: a way of working, a question they also can’t put down, a younger version of themselves. I’m still looking for my limits, and the fastest way I know to find them is working beside people who’ve already found theirs. Everything above is my evidence that the investment compounds.