Pricing

Free core. Enterprise when you need it.

The full local workbench is free for every machine. Enterprise adds the support, governance, and rollout help larger teams ask for.

Core

For individuals and small teams

Free · forever
  • Local chat with the full WebUI
  • OpenAI-compatible provider selection
  • Unlimited isolated workspaces
  • Durable memory, skills & markdown RAG
  • Controlled file access via local services
  • Expert panel with decision synthesis
  • Matbot plugin system — extend at runtime
Get started with the docs
FOR TEAMS

Enterprise

For organizations with governance needs

Custom · per rollout
  • Guided rollout & workspace design
  • Governance review: memory-policy, file scope, providers
  • Priority support with named contact
  • Custom plugin & expert development
  • Team onboarding and training
  • Compliance documentation package
Request a demo

Everything in Core is in Enterprise. Both run entirely on your machines.

Request a demo

Thirty minutes, your use case

We'll walk through the WebUI, set up a workspace shaped like one of your projects, run the expert panel on a real question, and answer whatever your security and compliance folks want to know.

Thanks! We'll be in touch within one business day.

Common questions

Does any data leave our machines?

No — Cortex runs entirely locally. Conversations, memory, file indexes, and RAG all live on the machine. The only outbound traffic is to the model providers you explicitly configure, and those can be fully local too.

What does “free core” actually include?

Everything Cortex does today: the WebUI, workspaces, memory, retrieval, controlled file access, and the expert panel. Enterprise adds services around the product — rollout, governance, support — not gated features.

How is this different from a cloud AI assistant?

Cortex is a composed runtime, not a hosted chatbot. Behavior is assembled from your workspace configuration and plugins, your data stays put, and compliance can audit each workspace independently.

What are the system requirements?

Windows, with PowerShell for the launch scripts. Model requirements depend on the providers you choose — hosted endpoints need almost nothing; local models need suitable hardware.

Can we add our own tools and experts?

Yes. Matbot remains the underlying runtime and plugin system — plugins can be added at runtime, and expert-specific files let you shape each expert’s knowledge per workspace.