Platform

One runtime. Every desktop OS. Any agent.

InvokeFlow operates unmodified applications on Windows, macOS and Linux — new or decades old — and gives every one of them a face any MCP-capable agent can call.

Three runtimes

Three runtimes. One protocol.

Composer · Desktops

Turns a real desktop into a programmable surface of real applications. Launch, place, call and close the software the machine already has — then save the arrangement by name and push it across a fleet.

Windows · macOS · Linux

Aria · Displays

The same protocol pointed at a screen. A programmable, observed surface of tiles for kiosks, floors, lobbies and rooms — governed the same way, recorded the same way.

Shipping in real deployments

Conductor · Fleet Console

What is running, where, across every device — with the same record behind it. The view an operator needs before a fleet is a fleet.

MQTT · HTTP · MCP

Same envelope. Same scopes. Same screen states. Same record. Same fleet.

How it works

Discover. Authorize. Invoke. Record.

What sets it apart

Five things, together.

In one runtime, across every desktop OS.

Reaches software as it exists

Unmodified applications, where they already run — without a vendor-authored plugin.

Runs many applications in concert

Pulls from one, acts in another, keeps them in sync as they change.

Re-resolves the target

Every command finds the exact live window again before it acts.

Does the work without taking over

The person stays in the seat. The agent works alongside them on the same surface, and either can take the controls.

Finishes the job and proves it

Uses the application’s own responses and live state where available, then records what ran and what proved it.

More than automation

Automation is where it starts. It isn’t where it stops.

The whole callable surface

The API is what the vendor chose to expose. The application can do more. We call all of it — every command the software already knows, with no plugin and no permission asked.

An MCP face for every application

Commands discovered from the running application are re-exposed as tools any MCP-capable agent can call — giving software that never shipped an interface a working one.

Composed workspaces

Your real applications joined into one live workspace, arranged for the task — grounded in the software itself, not a dashboard generated beside it.

Reasoning only where it’s needed

Routine steps run deterministically, with no model round-trip. Faster, and a fraction of the agent tokens. Your AI budget goes to judgement, not clicks.

Teach it by doing the work once

What it learns, it can run — in the same runtime — and prove it ran. It never records your screen to do it.

Your model, cloud or local

Bring the agent and the model you already chose. A local model works the same way as a cloud one — and nothing leaves the endpoint either way.

A live view of the estate. See what is running, where, and whether it is healthy, across every desktop — while the work happens. Over time, the record shows which applications and workflows your teams lean on most, so the next automation is obvious.

Start here

Start with one workflow.

Point InvokeFlow at the applications it lives in. It runs governed and on the record from the first command.