Private beta · by invitation

Meet the version of you that never logs off.

You run your whole business out of one head. Yours. Klyr puts your DNA into Claude, so it stops being a generic assistant and becomes your clone. The right hand you could never afford, that already knows how you work.

It remembers your projects, decisions, people and working style, then brings that context into every Claude Code session.

Never sleeps. Never forgets. Never complains.

See what it does

A Claude Code plugin · Built by an operator, not a marketer · 2 years in daily use

Every AI you've tried is a genius with amnesia.

Brilliant for ten minutes, then it forgets your business, your voice, why you killed that deal. Every morning you re-introduce yourself to a stranger.

You don't have a productivity problem. You're the bottleneck, and every tool you open starts from zero, not knowing you.

A tool waits for instructions. A clone already knows.

It remembers the client you met once, the call from three weeks ago, the reason you said no, from the work you choose to give it. It answers in your voice and pushes back the second you're about to fool yourself. And it does not only remember. It learns how you work and turns your own moves into reusable skills, so it gets sharper every week. You stay in the driver's seat: it proposes, you decide, it never acts behind your back.

A memory that can't forget

Give it what matters and it keeps every thread, sharp, no matter how much you pile on. The flaw that makes other tools go dumb over time, engineered out. And it's your memory: wipe anything, anytime.

Self-learning skills

From the work you do with it, it spots your repeatable moves and turns them into skills you can reuse. No setup, no prompts to maintain, and nothing runs without your say-so. Every week it is a little more you.

Two things, done right. Every rival ships forty features that look powerful and do no real work. Klyr ships the two that do, and nothing to babysit.

One head, leaking. Or one brain, compounding.

Without a clone

  • Ideas you drop and never recover
  • Re-briefing your tools from zero, daily
  • You are the ceiling, and you know it
  • When you stop, everything stops

With Klyr

  • Nothing worth keeping is ever lost
  • It wakes up already up to speed on your world
  • It gets sharper every single week
  • The routines you set run on schedule, in the background

Two ways in.

A senior right hand who actually knows your business runs over 80k€ a year, months to train, and then they quit. Your clone is alive today, never quits, never forgets.

Klyr Individual

For consultants, founders and operators who run the whole business out of their own head.

500€/ month2 months free
  • Your DNA, so Claude works the way you want
  • A memory that can't forget
  • A sparring partner with teeth
  • It learns your moves and turns them into skills you reuse
  • Runs the routines you set, on your schedule

Full access in minutes. Import as much or as little of your ChatGPT and Claude history as you want, so it starts already knowing you. Hosted in your region, always on, zero maintenance. Your data stays yours, wipe it anytime. 14-day money-back.

Klyr for Teams

Every person gets their own clone, on a tenant the company owns and controls. What your people build stays with the company, even when they leave. Far better than watching them pour company data into private AI tools you can't see.

  • Per-seat pricing
  • The company owns the data; admins manage the tenant
  • Hosted in your region

A 30-minute call. You leave knowing exactly how it fits your team and what it costs. Straight answers, no pitch.

"

I built the systems. I was still the one repeating myself.

I run my own firm, Asio Services. I'd written the SOPs, the playbooks, the systems. And I was still the bottleneck: a document doesn't think, and even a sharp team needs you to explain it again, and again.

So I built Klyr: it pours everything you know into Claude, so Claude works like you instead of like a stranger. Not another doc that gets ignored, a second brain that learns something once and never asks twice. Your decisions, your clients, your way of working.

For two years it has run my whole business beside me. Then I made it something anyone can install and run, not just me. So today it stops being mine and becomes yours.

Nabil. I built Klyr, and I run my firm, Asio Services, on it every day.

The questions you're actually asking.

Why not just build this myself?

You could. I did, over two years. Here's the trap: the memory part is the easy part. Anyone can bolt a notes database onto Claude in a weekend, and that is exactly what you get, a memory system that needs babysitting. The two years is turning that into a clone that thinks like you and stays sharp on any machine without rotting. You want to run your business, not become the maintenance engineer of your own brain-in-a-box. Klyr is the two years you don't spend.

Isn't this just a big system prompt or a CLAUDE.md file?

A file is a dead snapshot. It doesn't remember last week's call, doesn't grow when you decide something new, doesn't follow you across machines. You would spend your evenings feeding it by hand until it rots. Klyr isn't a file you maintain. It's a second you that shows up already up to speed and gets sharper as you work.

Claude has memory now. Why Klyr?

Claude's memory is real, and good: it learns your preferences from your chats, inside Claude. Klyr goes two layers deeper. One, it doesn't just note a few preferences, it builds a living model of how you actually think and work, on top of the identity you author yourself, so it acts like you, not like a tool that caught a few facts about you. Two, the part Claude has no answer for: your whole past, carried with you. Import your history from Claude, ChatGPT and OpenClaw, add everything you do in Claude Code, and your own notes vault, all kept on a timeline so last year and last week never blur into one. That's your second brain, not a chat summary. And it's yours: self-host it, take it anywhere, it never lives locked inside one app.

Why not OpenClaw, Hermes, or one of the other agent tools?

I ran both, for months, so this is my experience, not a spec sheet. OpenClaw started brilliant, then for me it rotted: pile on enough memory and it began hallucinating, mixing up my clients, contradicting decisions I'd made the week before. And I became its full-time babysitter, pruning, patching, restarting, a second job I never asked for. Hermes "fixed" that by capping its own memory, which to me is just a goldfish with a smaller bowl: it stays sane by staying dumb, forgetting you on purpose. Both buried me in flashy features that looked powerful in a demo and did no real work for me. And there's a structural risk worth knowing: Anthropic has already restricted third-party tools on Claude subscriptions once, and could again. Klyr doesn't run as an outside harness that pipes your subscription out. It runs inside Claude Code itself, the first-party path Anthropic keeps supported, the same place their own routines run.

Where does my DNA live? Is it private?

It's yours, and you can see it. Klyr only remembers what you give it inside Klyr, never your whole machine or your files behind your back. You can read, edit or wipe any memory, anytime, it's not a black box. It lives on your own machine, or your own private space in your region if we host it. When your clone thinks, it sends only what that question needs to Claude, on the Claude subscription you already have. We never read it, never train on it, never sit in the middle. You're the customer, not the product. Nobody gets a window into your head but you.

What do I need to run it?

Klyr is a Claude Code plugin. Today it runs on Claude Code, on Mac and Linux, or Windows through WSL. Coming soon: Codex, and native Windows.

Your business has run on one brain long enough.

Get in early: a direct line to me, and a hand in shaping your clone.