The cognitive layer for AI

Stop restarting
intelligence from zero.

Memory alone isn't enough. An AI can remember everything about you and still be clueless about what matters right now.

thinqOS is the cognitive layer for AI. It gives people, teams, and agents a digital mind: memory, plus the understanding and continuity to act on it, across every model, tool, and session.

In private preview · An AI4Outcomes product
Request Private Preview Read the Science →
digital_mind · active
conf 0.82 decaying
Context active across people, teams, and agents
Persistent contextNever start from zero
Living beliefsConfidence that decays and locks
One shared worldA mind per identity
Beyond memory

Three ways AI remembers.
Only one builds understanding.

An AI can have perfect recall and still be clueless. Memory hands it the facts. It doesn't say which facts matter right now, who they apply to, or how much to trust them. That last part is cognition, and it's the difference between a filing cabinet and a state of mind.

Chat History

Ephemeral

Stores the conversation, but the meaning fades the moment the session ends. Every new thread starts cold.

Fragile and easy to lose

Memory

Fact recall

Remembers facts and preferences, but detached from the situation that produced them. It recalls without understanding.

Useful, but limited

Digital Mind

Cognitive state

Maintains structured, evolving context (goals, evidence, relationships, and confidence) that travels with you across every model and tool.

Persistent, contextual, and actionable
Memory
Facts and preferences you can recall later.
+
Understanding
Which facts matter now, for whom, and how sure to be.
+
Continuity
The same context across every tool, model, and session.
=
A Digital Mind
Cognitive state an AI can reason with, not just retrieve.

Looking for AI memory? thinqOS is that, and the part most memory leaves out. Already have memory? This is the layer it's missing.

How it's built

A shared world of facts,
a mind for every perspective.

thinqOS separates what's true in the world from what each mind believes about it. Facts live once, in a shared world. Every identity, human or agent, holds its own perspective on them: how certain it is, how alive the belief is, where it came from, and who has seen it. The same fact can be held differently by you and by your agent. That split is what lets people and agents share one layer without sharing one blob.

Confidence

How certain this mind is about a belief, from 0 to 1, and its own value, not the world's. It eases down over time unless the belief is confirmed or locked.

Salience & Decay

How alive a belief is right now. Salience fades on a decay curve unless the belief is reinforced, so a mind stays focused on what still matters.

Source

How the belief arose: declared, extracted, inferred, observed, or consolidated. A typed record of why the mind believes what it believes.

Disclosure

Which identities have seen a belief, tracked per belief, so a mind knows not just what it believes but who else already knows it.

Read: Your AI Doesn't Need a Better Memory →

What it looks like

One fact,
two perspectives.

Context isn't a black box. A fact lives once in the shared world. Each mind holds its own read on it: its certainty, how alive the belief is, where it came from, and who's seen it. Here, you and your agent hold the same fact differently.

// The structure mirrors the real two-layer model:
// a shared proposition, plus a per-mind evaluation.
// Values shown are an example, not customer data.
refund_policy.mind Example 
# Shared world: the fact, stored once
proposition p-3920:
  summary: "Refunds over $200 need manager approval"
  subject: entity:refund-policy

# Your perspective on it
evaluation (you):
  confidence:   0.92
  salience:     0.80
  source:       declared
  protection:   locked      # you confirmed it
  disclosed_to: [you, agent:support]

# Your agent's perspective on the same fact
evaluation (agent:support):
  confidence:   0.74
  salience:     0.41      # decaying, unreinforced
  source:       inferred
  protection:   none
  disclosed_to: [agent:support]
Living beliefs

A mind doesn't just hold beliefs.
It forms them.

thinqOS doesn't only store what it's told. It derives new beliefs, abstracts patterns from many, and lets all of them strengthen, fade, or lock over time, the way memory actually behaves.

Infer

The mind derives new beliefs from what it already knows, and keeps the ones that prove useful over time.

Consolidate

It abstracts higher-order beliefs from many specifics, turning scattered facts into general understanding it can reuse.

Decay

Every belief loses salience over time on a decay curve, damped by how emotionally charged it is. What you stop touching quietly fades.

Reinforce

Bring a belief up again and it strengthens. Repetition and relevance push salience back up and reset the clock.

Protect

Confirm a belief and it's protected from decay. Lock it and it won't fade or be overwritten. Three levels: none, confirmed, locked.

Forget

Forget a belief and the inferences that leaned on it are defeated in a cascade, so nothing keeps standing on a fact you removed.

Reconcile

When a new belief collides with an old one, the mind surfaces the conflict instead of silently overwriting. It supersedes what's outdated, keeps the old version as history, and updates what it now trusts.

Inside a digital mind

Not just what a mind holds, but what it tracks.

Goals

What the identity is trying to achieve.

Preferences

What it likes, values, and avoids.

Working Notes

Live thoughts, plans, and open questions.

Procedures

Learned how-to: the steps it knows for getting something done.

Relationships

Who and what connects: trust, relation, and links between them.

Confidence

How certain the mind is, tracked per belief.

Salience

How alive a belief is right now, and fading.

Source

How it arose: declared, extracted, inferred, observed, consolidated.

How it works

Capture once. Structure it. Reuse it everywhere.

1

Capture

Capture context from your conversations and documents, and harvest the work you do in other AI tools, so a strategy you set in one place and a decision you make in another land in the same mind instead of scattering across apps.

2

Structure

Organize them into a reusable cognitive state. Not just stored, but resolved into beliefs with confidence, salience, and source.

3

Reuse

Activate the right context across people, agents, tools, and sessions, so every interaction starts aligned instead of from scratch.

Built for humans and agents

One cognitive layer, doing two very different jobs.

Underneath, it's the same engine: a digital mind for an identity. But giving yourself continuity across the tools you use, and giving the agents you build a mind that persists, are two different stories. thinqOS does both.

For Yourself

Carry your own mind across every AI you touch. thinqOS holds what matters to you and keeps each model and tool aligned to your goals, across tools, across contexts, across sessions. You stop re-explaining yourself, and you never start from zero.

Personal contextAcross toolsAcross contextsContinuity

For What You Build

Give the agents you ship a persistent identity: goals, preferences, procedures, and beliefs that survive restarts. Each agent gets its own mind, isolated by default. They consult and delegate to each other, instead of waking up blank every run.

Agent identityIsolated mindDelegationContinuity

Building with AI coding agents like Claude Code? See thinqOS for Developers →

Trust by design

Private by default, and yours to steer.

One Mind, One Owner

Each identity has its own mind, and minds are isolated by default. No agent can read another identity's mind. Privacy is the architecture, not a setting.

You Steer What's Remembered

Confirm a belief, lock it, edit it, or forget it, one at a time. Turn capture off per conversation. The mind only keeps what you let it keep.

Inspectable, Not Opaque

The mind is readable, queryable structured state, never a black box. Every change is recorded, and every time a belief enters context, it's logged.

On the roadmap

Built for more than it does today.

These are seeded in the architecture and coming through preview. We'd rather show you the line between what runs now and what's next than blur it.

Planned

Share, with whom

Disclose a belief to a specific person or agent on purpose. The per-belief disclosure layer is already in place; user-driven sharing is next.

Planned

Governed reuse

Policies over what's shared and how, once minds can share. Today an inference firewall already constrains what surfaces.

Planned

Minds that align

Cross-mind consolidation, so a team of agents can converge on shared understanding. Today, minds stay isolated by design.

Planned

Source-linked evidence

Trace a belief to the exact message or passage it came from. The evidence layer exists; message-level provenance is planned.

Who's building this

Built by people who've shipped
context infrastructure before.

thinqOS is built by the team at AI4Outcomes, an AI-native product portfolio based in Ontario, Canada. Its founder is a primary inventor on multiple patents related to data and AI context, the exact problem of giving AI trustworthy access to what matters. The work toward a persistent cognitive layer has been years in the making, and thinqOS is where it comes together.

An AI4Outcomes productExplore the portfolio →
Dan DeMers

Dan DeMers

FOUNDER

Primary inventor on multiple patents related to data and AI context. A career building data and AI infrastructure, with earlier roles in markets at RBC and Citigroup.

Jenn DeMers

Jenn DeMers

CO-FOUNDER · OPERATIONS

Operations, execution, and company-building across the AI4Outcomes portfolio, spanning enterprise environments and scaling-business operations.

Building in the open
Why memory won't fix AI
Read →
Building in the open
One world, two minds
Read →
Building in the open
The shared notebook
Read →
Access

Private preview,
opening in waves.

thinqOS is in active development. We're opening access gradually and matching each team, agent, or builder to the right preview. Tell us how you'd use a digital mind.

Request Private Preview
Builders shipping AI agents and productsGive your agents persistent identity, goals, and shared context that survive every session.
Teams standardizing how AI uses contextOne inspectable layer for what your AI knows, consistent across the models and tools you use.
Individuals who want continuityStop re-explaining yourself to every model. Carry one digital mind across all of them.

Build a digital mind for yourself,
your team, and your agents.

Request Private Preview See How It Works →