Skip to main content
y.computer
Get a U.S. quote

Y OS · local AI without the infrastructure hobby

Your AI, in one private workspace.

Y OS deploys models, chat, documents, code, voice, agents and a local API onto supported AI hardware—then keeps the whole configuration pinned, observable and recoverable.

Check my hardwareGet it with Y Computer
Y

Y OS

QUALIFIED PROFILE · AUG 2026

Local is a visible state, not a vague promise.

Every model and tool carries a data-boundary badge. A green Local badge means no external AI provider. External means a connection can leave your network and must be enabled deliberately.

LOCALCONTROLLEDEXTERNAL
LOCAL

Chat

One familiar workspace for selected local models.

LOCAL

Documents

Search only the folders you choose, with source citations.

LOCAL

Code

Profiles for editor tools through one authenticated endpoint.

LOCAL

Voice

Offline transcription and read-aloud without uploading audio.

CONTROLLED

Agents

Curated tools set to Allow, Ask or Block—never blanket access.

EXTERNAL

Connections

Web, email and cloud services are optional and visibly labeled.

What Y OS actually is

A supported system, built from open parts.

The launch version is deployed on top of a supported, customer- or OEM-licensed Linux installation. We qualify how the parts work together and own the handover, update and recovery path.

  1. WorkspaceChat · Documents · Code · Voice · AgentsWhat your team sees
  2. Y control planeIdentity · model profiles · permissions · updates · diagnosticsWhat Y qualifies and supports
  3. Local APIOne authenticated OpenAI-compatible /v1 endpointWhat your applications use
  4. Inferencellama.cpp · vLLM · qualified ROCm or CUDA imagesPinned per hardware profile
  5. HostCustomer/OEM-licensed Linux installation on supported hardwareY OS is deployed on top

Security baseline

Private by architecture. Boring by operation.

No mystery telemetry, no default public endpoint, no agent with the keys to the whole machine. The secure configuration is the default configuration.

  • 01

    Full-disk encryption and unique credentials during onboarding

  • 02

    Inference services bound to the machine, not exposed to the public internet

  • 03

    Remote access through a private tunnel—not an open port

  • 04

    Tools run with explicit permissions and isolated execution profiles

  • 05

    Model source, license, revision and file hashes recorded in a manifest

  • 06

    Diagnostics are customer-triggered and redact prompts and documents

RELEASE POLICY 1

Security moves quickly

Operating-system security updates can follow a maintenance window, with customer-visible release notes.

RELEASE POLICY 2

AI runtimes move carefully

GPU drivers, kernels and inference engines stay pinned until the complete combination passes load, context, tool and thermal tests.

RELEASE POLICY 3

Models never change silently

New checkpoints are opt-in because behavior, prompt formats, licenses and resource requirements can all change.

RELEASE POLICY 4

Every release can go back

Pre-update snapshots and a retained last-known-good profile provide a documented rollback path.

Fastest way to start

Put Y OS on hardware you already own.

Compatibility check, qualified deployment, selected model set, onboarding and a benchmark certificate. Approved customer-owned or unchanged U.S.-market OEM hardware only for the founding release.

$2,000

one time · compatibility confirmed first

Check my hardware

Turnkey option

Get Y OS with a Y Computer.

Mini 128, Pro 64 and Max 96 configurations for one power user, parallel team services, or maximum CUDA compatibility. The exact bill of materials and U.S. terms are confirmed before payment.

From $5,999

founding-batch target · before tax and shipping

Compare Y Computers

Questions, answered plainly

Is Y OS a new Linux distribution?
No. The launch version is a signed deployment, configuration and support layer installed onto a supported customer- or OEM-licensed Linux system. Y does not redistribute a modified Ubuntu image. The value is the qualified configuration, control plane, model manifests, security policy, updates, rollback and support—not pretending we invented every open-source component.
Can I buy Y OS without a Y Computer?
Yes. The fastest U.S. launch offer is a $2,000 one-time deployment on approved hardware you already own or buy from an approved OEM channel. We confirm compatibility before invoicing.
Does it work without the internet?
Local chat, local document search, transcription and the local API can run without an external AI provider after the models are installed. Optional web search, email, cloud models and remote support require a network and are labeled External.
Is support a subscription?
The founding deployment price is one-time and includes the stated onboarding and first-year qualified update window. Any optional support after that will be quoted separately; local inference itself has no per-token charge.