CEX

Project / About

Continuity is the product.

CEX exists because useful AI work should survive a tab, a model change, and tomorrow morning.

The idea

A system around intelligence

A model can answer a prompt. It does not automatically remember a project, keep a goal active, reuse a method that worked, or apply your rules to the next task. CEX is the runtime that provides those durable parts.

You choose the model. CEX keeps memory, tools, skills, policies, goals, and workspaces available around it.

The distinction

Not another wrapper

CEX is designed as a persistent partner rather than a disposable chat session. The same project state can remain available when the model changes, and power stays behind visible permissions instead of being hidden behind vague automation.

Model-independentRun a local model or connect a provider with credentials you control.
Local firstRuntime state, workspaces, and fresh memory stores stay on the machine by default.
InspectableTool calls, policies, goals, and runtime state are designed to be visible in the product.
ReusableSkills and memory carry proven methods forward instead of forcing the user to repeat them.
Founder-stage software

Built before it was polished

CEX began as a solo project on consumer hardware. The architecture is real; packaging, onboarding, documentation, and platform coverage are still being hardened.

The Linux beta is public first because it is the build that exists today. Windows and macOS will not be presented as available until their native packages are built and verified.

Early does not mean imaginary.

The product is usable, but the project is still learning where the runtime holds up and where it gets in the way. Specific, reproducible feedback is part of the build process.