Training copilot · AI-native · Open source

The training copilot that reads your form of the day

In 2018 I launched a training SaaS. In 2026 I unplugged it and rebuilt it AI-native: zero server, zero account — it runs on your own AI. It reads your day — load × feel — and tells you green, amber or red, and above all why. It reads; you decide.

Free · Runs on your own AI · Zero infra · Open code.

I stopped developing feezify in September 2026. The code, the method and the docs stay open.

By Nicolas Jouanno — frontend developer, former pro cyclist. The method is his racing judgment, encoded.

The problem

You're training blind on one of the two axes

First trap: you listen to the numbers. Fresh form, low load, the app says “go” — and you push through a day your body was clearly refusing. A week later, you pay for it.

Second trap: you listen to your morning mood, and you miss the days you were genuinely ready to push.

“We program the load. We forget the state of the person absorbing it.”

The method — open on purpose

Cross your load with how you feel

The real subject is neither the numbers nor the feel alone. It's the crossing of the two — and knowing, in doubt, which one wins.

  • 01 · OBJECTIVE

    The load

    From your activities, feezify computes your load as true exponential averages (TSS → CTL / ATL / TSB). TSB gives your form. It's deterministic — math, not an opinion.

  • 02 · SUBJECTIVE

    The feel

    Your journal gives your real readiness: sleep, fatigue, motivation, stress, how the legs feel, what's happening outside sport.

  • 03 · THE CROSSING

    The read

    feezify sets a light — green, amber or red — and, above all, the explanation. The colour isn't up for debate; the why is in plain words.

The rule — the one that carried all the value of the old app: the subjective gates the objective.

  • Injury or illness → always red.
  • Low readiness → never green.
  • Fresh legs never override a body saying no.

The method is public, on purpose: it's the point, not a secret. Read it in full →

Try the rule

Three real mornings. Same math, different bodies — watch which side wins.

Green — go.

Readiness high, form non-negative. Both sides agree: today can take quality.

Let's be plain: feezify is a copilot, a reading assistant. It prescribes no workout, never tells you what to do, replaces neither a trainer nor a doctor. Weight, for instance, is only read as a trend — never as a diagnosis. The decision is yours, always.

AI-native · zero infra

On your own AI. Not on my server.

feezify is no longer an app I host. It's a skill + a markdown core you own, installed on your AI (Claude, OpenClaw). The old web app maps tier for tier onto the new agent:

Classic web app The tier AI-native feezify
Browser / frontend interface The LLM / the chatbot — Claude, OpenClaw
Server / backend engine The agent — a pure, unit-tested method core + adapters (Strava…)
Database persistence A second-brain memory — your journal + the copilot's compiled memory of you
  • Yours, locally

    A portable folder of markdown you own. No server, no account, no telemetry. A connector (Strava…) stays off until you switch it on.

  • Two memories

    Your journal, which you write; and the memory the copilot compiles about you over time — every claim traceable to a precise day.

  • Open & provider-agnostic

    Strava is just an adapter; the engine depends on no brand. The code and the method are in the open — read them, judge them, fork them.

Project story

From SaaS to AI agent

The story behind this rebuild lives on Substack. It continues the journey told in From cycling to the web.

Who it's for

Serious about training. Honest in a journal. At home with an AI.

  • You train seriously — bike, run, endurance — and you record your sessions.

  • You keep — or you're ready to keep — an honest journal, even a short one.

  • You want to read your form more clearly, not to be told your workouts.

  • You're comfortable with an AI (Claude, OpenClaw) and the idea of a tool with no app, no account.

The kind of profile? The triathlete who runs Claude; the runner who loves their data but won't be told their session. It's not for you if you want a turnkey plan dictating every workout: feezify doesn't prescribe.

Install

Clone, build, ask.

The no-terminal zip was never published. What works is the developer path: a terminal, Node and pnpm. Same engine on Claude and OpenClaw.

  • STEP 1

    Install and build

    git clone https://github.com/jn-prod/feezify
    cd feezify
    pnpm install && pnpm build
  • STEP 2

    Create your core

    cp -r core-template ~/my-feezify-core

    Your private folder: baselines, sport, journal. Strava stays optional: your tokens go in .env, and feezify can read your day from your journal alone.

  • STEP 3

    Ask for your read

    Point your AI at the skill's SKILL.md (Claude or OpenClaw), then ask: “How am I today?”

Follow the developer path →

Documentation

Everything is written down. Read it.

The full manual ships with the site — the idea, the method, the install, privacy. Version française

FAQ

Frequently asked questions

Is feezify a program that gives me my plan?

No, and it's deliberate. feezify reads your day and tells you green / amber / red, with the why. The decision stays yours. It's a copilot: it illuminates, you decide.

Do I need a subscription or a server?

No. There's no app to host, no account to create. feezify is a skill + a markdown folder running on your own AI. Zero infra.

Where does my data go?

Home. Your core is a folder of markdown on your machine. No feezify server, no telemetry. A connector like Strava stays off until you switch it on yourself.

Which AI do I need?

An AI that supports skills — Claude, or a self-hosted agent like OpenClaw. You install feezify on it, and ask it how you are today.

Do I need to know how to code?

Today, yes: enough to use a terminal. The install means cloning the repo and building it. The no-terminal path, a zip to upload in Claude, was never published.

What about my watch — Garmin, sleep tracking, HRV?

Activities come in through Strava, the only adapter built. The engine is provider-agnostic by design, so a watch provider would be an adapter, not a rewrite. Sleep, fatigue and feel enter through your journal — your watch's numbers can inform what you write, and an honest line about a bad night often reads truer than a sleep score.

How is this different from analyzing Strava myself?

Strava gives you numbers. feezify crosses them with how you feel, applies a rule (the subjective gates), and returns an explained read — not one more table to interpret alone.

Is it ready?

The core works and the repo installs. I stopped developing it in September 2026, so don't expect new features. The code stays open: read it, judge it, fork it.

feezify doesn't try to train you. It helps you read yourself.

I stopped developing it in September 2026. A tool that reads your day — no server, no account, no orders — stays open: read the code, fork it.

Built in the evenings, in the open, by Nicolas Jouanno — frontend developer, former pro cyclist. Free and open source for everyone.