01 / AOS

Clear boundaries.
Connected responsibilities.

Explore the layers designed to turn a request into a plan, an allowed action and a verified outcome.

  1. Defines the goal and permission; takes control when needed.

  2. Turns a request into a goal, scope and success criteria.

  3. Owns the observe → decide → execute → verify loop.

  4. Produces plans, diagnoses, visual assessments when needed and recovery proposals.

  5. Supports selection among finite allowed options.

  6. Checks scope, permission, ownership and current state independently of the model.

  7. Dispatches a validated typed action to the appropriate tool adapter.

  8. Provides authenticated, controlled access to the isolated computer.

  9. A separate workspace for file, application, browser and desktop tasks.

  10. Compares the result with the task’s independent success criterion.

  11. Aims to persist canonical task state and events in SQLite-backed records.

  12. Separates model, adapter, deployment and benchmark identities; routes compatible capabilities.

Target architecture · Select a component to inspect its responsibility and boundary. The diagram is not evidence of running services.

Text equivalent of relationships
  • User & human control → Request & scope → Task Normalizer
  • Task Normalizer → Typed goal → Operator
  • Supervisor → Plan → Operator
  • Decision Engine → Selection support → Operator
  • Operator → Action proposal → Safety Policy
  • Safety Policy → Allowed command → Executor
  • Executor → Allowed command → Computer Gateway
  • Computer Gateway → Allowed command → Agent Computer
  • Agent Computer → Observation → Outcome verification
  • Outcome verification → Verification → Operator
  • Outcome verification → Record → State / Trajectory Store
  • Operator → Diagnosis request → Supervisor
  • Registries / Capability Router → Compatible candidates → Decision Engine
  • State / Trajectory Store → Reviewed record → Data preparation & quality
  • Data preparation & quality → Versioned data → Offline training
  • Offline training → Candidate → Held-out evaluation
  • Held-out evaluation → Evidence for decision → Explicit release decision
  • Explicit release decision → Authorized promotion → Registries / Capability Router

This site explains AOS. The services below are target architecture; the working application will be developed in a separate repository. Read the scope ↗

Two roles.
One control loop.

Supervisor plans. Operator owns the loop. Safety Policy independently allows or stops an action.

One active task, one active action, one computer-input owner. Canonical state is designed to live outside chat in SQLite-backed persistent records.

The right tool.
Through an allowed route.

Access to a more direct tool does not expand authority. Every route is subject to the same policy checks.

  1. 01Suitable internal API
  2. 02File, process or Agent Computer shell
  3. 03Browser DOM / CDP
  4. 04Accessibility interface
  5. 05Visual observation, mouse and keyboard

Host shell is a separate administration surface, excluded from the initial autonomous toolset. CachyOS is a target host preference, not a verified support matrix.