Make your expertise the operating system.
AI just runs it.

Your notes, prompts and skills in a plain-text library available across your projects, devices and teams. Run on any AI.

If you're not running one of your own methods from your library in 7 days, don't pay.

Connecting an assistant — your library, reachable from Claude, ChatGPT or Cursor
Your library — notes, prompts and skills, kept as files you own

1. Connect any AI — 2. Your library, available everywhere

The problem

You're repeating yourself to AI.
And what it learns, it won't share.

Every task you give to AI needs the same things: the job to do, the rules to follow, the relevant data, the examples that worked before. In short, the context.

You rebuild context by hand every session. In long sessions, it grows too large and starts to "rot." Your work gets lost in chat transcripts you'll never reread. You get deliverables, but nothing you can reuse or hand to a colleague.

Assistants offer project folders and "memory" to organize and remember your stuff. Then they rent it back to you.

The library

Your operating system is a folder of files.

Notes, prompts and skills in plain text. Some you write. Some you borrow. Some you generate from the body of work you already have.

Your library is yours. Curated by you, for the work you do. Accessed from the tools you use, now and in the future. And exported whole in one click.

Choosing an AI app to connect — Claude, ChatGPT or Cursor

Every AI app

Read and write your library in Claude, ChatGPT, any app that speaks the standard.

A company's library — folders nested inside folders, with a skill and a prompt among the files

Every device

The same library whether working at your desk, on your laptop or on your phone.

A shared library's member list

Everyone you work with

One shared library the whole team runs — not a copy that goes out-of-sync. Every member keeps a personal library too, and stats show what you and your team actually use.

Your library grows and travels with you.

A better way to work

Just read, write and run.

LLMs work better in files than in chat. A specific task or todo? Make it a file. How to do it? Links to other files: the style guide, the prior art, an agent skill. Unlike chat, every important element can be refined and reused.

Developers got here first. They call it "spec-driven development." More broadly, reference-driven work is a revelation. Documents are the love language of LLMs — and intelligent humans, too. 😉

Ownership

AI keeps changing. Your library doesn't.

Plain text files you can see and take with you anywhere.

Revision

Nothing sticks without your say-so.

Everything written to your library is a version you can keep or roll back.

Compounding

What you learn once, you keep.

A method that worked becomes a file. Use it next time, or hand it to a colleague.

Every task gets its own fresh context — the files you chose and nothing else. No bloated history, no context rot.

In the cloud

Dispatch more. Close the laptop.

Big tasks, in one shot: many turns of real work, unattended.

Many at once, at arm's length.

Runs happen off your machine, in a secure sandbox. Only the result comes home.

Four runs going at once in the cloud, two still working and two finished

Every asset, accounted for.

How each file came to be: the prompts that ran, the models used, what it cost.

Two documents from one process — the step that made each, the model that wrote it, and what it cost

Kick off AI work from anywhere. Work runs with your laptop closed.

Pricing

Solo or team. Your machine or ours.

Pro

Your personal library of notes, prompts and skills that works with any AI

$29 / month

 

Start my library

Cloud adds

  • Kick off AI work from anywhere
  • Work runs with your laptop closed
  • Run many tasks at once
  • A secure sandbox for every run
  • An audit trail of every step
  • Unlimited notes, prompts and skills
  • Reachable from any AI tool over MCP
  • Can run on your own machine
  • With Cloud: 50 hours of cloud compute per month
  • With Cloud: Cloud workspaces for file- and data-heavy projects
  • With Cloud: Connect your Claude or ChatGPT subscription, or bring your own API keys
  • With Cloud: Or buy credits and run on ours

Team

Your shared library of notes, prompts and skills that works with any AI

$87 / month

 

Start my library

Cloud adds

  • Kick off AI work from anywhere
  • Work runs with your laptop closed
  • Run many tasks at once
  • A secure sandbox for every run
  • An audit trail of every step
  • Unlimited notes, prompts and skills — private or shared
  • A personal library for every member, alongside the team's
  • Includes 3 seats
  • Additional seats $29/mo each
  • Reachable from any AI tool over MCP
  • Can run on your own machine
  • Unified team dashboard and controls
  • With Cloud: Additional seats $89/mo each
  • With Cloud: 50 hours of cloud compute per seat (150 hours included)
  • With Cloud: Cloud workspaces for file- and data-heavy projects
  • With Cloud: Connect your Claude or ChatGPT subscription, or bring your own API keys
  • With Cloud: Or buy credits and run on ours

About a quarter of a Claude Max or ChatGPT Pro subscription.

Need SSO, custom data terms, dedicated support or volume pricing? Contact us

Frequently asked

Before you ask.

If I shouldn't be locked into an app, why is FactorIn one?
Because a folder of files cannot be reached from anywhere, shared without going out of sync, or carry provenance and version history. That is what we add. The files themselves stay plain files — if something better comes along, take them to it.
Do I have to stop using Claude or ChatGPT?
No. That is the point. Your library appears inside the assistant you already pay for, over the same connector standard it already uses.
What happens to my files if I stop paying?
They stay yours. The account goes read-only, and the whole library exports in one click as plain markdown you can read and write without us.
Who pays for the AI itself?
You do, on your own subscription or API key — or on credits you buy from us. The plan buys the library and the compute; the model's bill is never bundled into it.
What is the difference between Pro and Pro Cloud?
Where the work runs. On Pro, your own machine does the running and has to stay awake until the work finishes. On Pro Cloud, our machines do the running, so several tasks go at once and finish with your laptop closed.
Is my library private?
Yes. Nothing is public and nothing is shared unless you put it in a shared team library.

The best AI is Actual Intelligence.

Capture it. Refine it. Reuse it. Share it.

Start my library