---
title: Why instibrain — everyone uses the same models
description: Why a company that uses the same models as everyone needs its own brain: its AI stops answering generically, a fix reaches every AI, and the pages stay yours.
url: https://instibrain.ai/why
updated: 2026-11-03
site: https://instibrain.ai/llms.txt
---

# Everyone uses the same models. The difference is what yours knows.

Your model is everyone's. What it knows about your company is yours alone, and it knows only what your team wrote down.

Request access  →  Connect Claude Code

everyone's

only yours

pricing/floors.md v41
clients/acme.md v18
rules/discounts.md v7
postmortems/q3.md v2

Anyone can use the models on the left. Only your AI reads the pages on the right.

every day

## Your AI stops answering generically about your company.

A recurring task starts from the current page, not from an old chat. Ask about a client, a deadline, or a rule, and the AI you use reads the page first.

-
It reads first The brain's first rule to every AI: read the space's `CLAUDE.md` before anything
-
It can name the page An answer that says where it came from is one you can check
-
You explain the company once Not again in every session, to every AI

Claude Code, on our brain

What is open on the Lisbon office, and who owns it?

search_brain Lisbon · read_node roadmap.md read

Who owns it: Maren. The roadmap's owner table (`roadmap.md`) lists the Office item as Maren's, due in November. It's goal #2 for Q4 2026, “Open the Lisbon office.” … What's open: the Lisbon lease renewal. An inbox item from 2026-10-25 says “call Tobias about the Lisbon lease renewal before Friday.” Nothing shows it was done.

The run is ours, on this server; Northwind Studio and its people are invented. The page grounds the answer; the model can still misread it. We use it first: the AIs that build instibrain and this site read an instibrain brain over MCP.

the team

## Fix the page once, and every AI reads the fix.

A procedure has one page. Edit it in the browser or in your editor, and every AI of everyone who reads the space gets the new text on its next read. Nobody keeps a copy of their own.

The page, edited in place; every AI of everyone who reads the space gets the new text on its next read.
-
One page, edited in place In the cockpit, or as a file on your computer
-
Every AI, next read Claude Code, Codex, and Claude on a phone read the same version
-
The old text is kept A version, with its writer; a bad edit is never the last word

A colleague needs the space, and their AI reads again before it answers. The editor · version history.

next year's model

## Change the model. Keep what it knew.

Switching models used to cost everything you taught one. The next model reads the same pages on its first day, from the same address.

month one   gpt-5
pricing/floors.md  rules/discounts.md
month six   claude-opus-5
clients/acme.md  deals/declined.md  postmortems/q3.md  rules/discounts.md  pricing/floors.md
year one   gemini-3
runbooks/deploy.md  architecture/schema.md  onboarding/week-one.md  postmortems/q3.md  deals/declined.md  clients/acme.md  rules/discounts.md  pricing/floors.md
year two   whatever ships next
contracts/promised.md  playbook/objections.md  onboarding/week-one.md  architecture/schema.md  runbooks/deploy.md  postmortems/q3.md  deals/declined.md  clients/acme.md  rules/discounts.md  pricing/floors.md
Above the line, the model anyone can use. Below it, your pages, all still there. The models and the pages are an example.

One command connects each AI: Claude Code · Codex. A sealed space opens on your computers alone.

ownership

## Read what your AI reads, and correct it.

The markdown your AI reads is on your computers and in the cockpit. Open it, see who wrote each block, change a line, and keep the folder with or without us.

-
Files on your computers `~/instibrain/spaces/`, kept in step by the sync client
-
Every writer named A person, a computer, an AI, or an agent, on each version
-
No model trained on it Your pages train no model and are never sold

Spaces: every space you read, and your role in each.

Roles, rooms, and the history our server keeps are not files. What you keep if we disappear · the sync client.

your security review

## Choose who reads each space, and what our server can read.

A space gives one body of knowledge one audience. A sealed space adds protection from us: encrypted on your computers, ciphertext here.

A sealed space in the browser: no key here, so nothing to read.
-
One audience per space Shared whole; what only some people should read gets a space of its own
-
Sealed: 0 bytes we can read Encrypted before it leaves your computer, the path included
-
The honest sentence The host cannot read a sealed space. Your computer and the model see what they read

An open space our server reads on purpose; names, counts, sizes, and timing leak; removing someone cannot recall what they pulled. For the person who runs your security review, every limit.

what it is not

## A wiki, a search, and the vendor's memory each do a job.

Each is a product someone else makes well. Four questions tell them apart from a brain.

| The question to ask any of them | A wiki | A search over your tools | The model vendor's memory | A brain |
| Who can read the plaintext? | The vendor, and everyone with access | The vendor's index | The model vendor | Open: us and its readers' AIs. Sealed: its admitted computers only |
| What do you keep if the vendor vanishes? | An export, if one is offered | Nothing; the index was theirs | Nothing | The folder of markdown already on your computers |
| Which model is it tied to? | None, and none reads it | The vendor's | That vendor's | Any AI you connect, this year's or next's |
| Who corrects a wrong line? | Whoever notices, if they may | Nobody; it is an index | Not visible to you | Anyone who reads the page, with every version kept |

## What your team writes down today, every AI you use reads tomorrow.

Request access for your company, read the use cases, team by team, or see who builds instibrain.

Request access  →  The use cases

---

instibrain is made by WebWork AI, Inc. Everyone uses the same models · the difference is what yours knows.
