OmniXela Product overview

XELA

A persistent, interruptible AI assistant that lives on the desktop, on the phone, and in the cloud — with memory it can be taught, and hands it can be trusted with.

1. What it is

XELA is an assistant with four parts that work as one:

LayerWhat it is
BrainA Cloudflare Worker with 45 stateful components (Durable Objects) driving the cognitive pipeline — comprehension, memory, emotion weighting, planning, and a language stage. Stateful and conversation-aware, and interruptible mid-thought.
Model layerA companion worker that routes to Workers AI models for language, vision, speech-to-text and text-to-speech. No third-party API keys to manage.
Desktop appA floating, always-on-top mascot on Windows. Click to talk, drag to move, tray icon, wake word, screen and camera awareness.
Mobile appAn installable web app (PWA) on any modern phone. Chat, voice, camera, tasks and memory, no store approval needed.

It is not a chat window with a skin. The assistant has a persistent self: what it remembers, what it is allowed to touch, how it speaks, and which brain it talks to are all things the owner controls.

2. What it can do to itself

Self-management, all of it visible to the owner:

What it cannot do to itself: it cannot rewrite its own instructions or model weights, cannot deploy or replicate itself, and cannot grant itself a permission. Every capability toggle belongs to the owner, not to the assistant.

3. What it can do to others

Actions that reach outside the app, each behind an explicit permission and an audit entry:

CapabilityScopeGuard
Open links, apps, filesAnything the OS can launchPermission + confirmation per action
Type and send keysThe currently focused windowPermission + confirmation, keystroke log
Control smart devicesHTTP switches (Shelly, Tasmota, ESPHome), Home Assistant, camera snapshotsDedicated IoT permission, per-action audit
Write filesIts own sandbox folder onlyPath confinement; cannot write to system paths
NotifyOS notifications for due tasksNone needed; read-only

It never contacts third parties on its own. There is no email sending, no messaging, no posting. Anything that leaves the device is either a model request to the operator's own cloud worker, or an action the user approved in that moment.

4. What it does on the user's behalf

5. Where it differs from general assistants

XELABrowser / OS assistants
PresenceFloats above other windows, tray, wake word, always availableInside a browser tab or a fixed panel
MemoryPersistent, inspectable, editable by the ownerMostly per-conversation or opaque
InterruptionYou can change your mind mid-generation; it adapts or asksTypically queue the message until the current reply ends
HandsFiles, apps, keystrokes, smart devices — under permissionRarely beyond the browser sandbox
OwnershipYour Cloudflare account, your data, your model choices, switchable brain endpointVendor-hosted, one size
Cost shapeUsage-based infrastructure, no per-seat licencePer-seat subscription

6. Deployment and data

7. Honest limitations

Anything offered to a customer should come with these stated up front:

8. Who it fits today

Best suited to a single professional or a small practice that wants one assistant across desk and phone, with memory of their work and the ability to act on it — and an owner who is comfortable granting permissions deliberately.

Not yet suited to: multi-location enterprises needing central administration, regulated clinical data handling, or teams expecting per-seat licensing and SSO.