AIIn Development
AI Runtime
Run compatible models across every surface.
Overview
What AI Runtime is
A runtime for executing compatible models across cloud, desktop, edge and open architectures through one interface, so which surface a model runs on becomes a deployment decision rather than a rewrite.
Data handling
Local first, consent gated.
- Local by default
- Work and traces stay on your machine unless you choose to send them.
- Consent per decision
- Sharing is opt-in at the point it would happen, not a setting buried at install.
- Secrets redacted
- Credentials are stripped before anything is eligible to leave the machine.
- Your provider keys
- Model access uses keys held in a local vault: the project uses your keys, not a shared account.
Deployment surfaces
- Cloud
- Desktop
- Mobile
- Edge and embedded
- RISC-V targets
Depends on
- The portable runtime
- Device profile definitions for constrained surfaces
Development
Where the work stands.
Objectives and dependencies. Dates appear only where a specific verifiable event backs them.
Next(1)
AI Runtime
In DevelopmentRun compatible models across cloud, desktop, edge and open architectures through one interface.
- Depends on
- Portable runtime
Related