All projects
01 / 08Active evolution
LOCAL AI OPERATING SYSTEM
CIEL + NOBI
Two generations of an AI assistant idea: NOBI explores broad autonomy, while CIEL rebuilds that ambition around narrow execution layers, safety gates, and observable results.
What this project is trying to make possible.
Explore how an assistant can participate in a user's digital environment while keeping local actions understandable, bounded, and recoverable.
A plain-language view of the system.
- A command enters a strict classifier and execution pipeline.
- The executor applies safety checks, permissions, and timeouts.
- A narrow agent delegates the request to one atomic skill.
- The system returns a structured result that can be inspected and tested.
What the project demonstrates today.
Where the next useful versions could go.
- Planner and task decomposition
- Permissioned voice and vision skills
- Visual execution console
- Memory and recovery phases