System Overview

NOME maintains state across sessions, models, and devices. Historical context, user preferences, project architectures, and interaction nuances persist in vector stores and continuously updated knowledge graphs.

Memory retrieval is thread-aware and project-aware — it finds what matters when it matters, built for long-running projects instead of session amnesia.

NOME classifies intent, assigns roles, and determines effort budgets for every request. Routing decisions consider workload type, complexity, latency requirements, and cost constraints.

The routing layer is deterministic-first with explicit route policy. When a selected model, seat, key, or host cannot run, NOME fails closed with a visible reason instead of silently switching providers.

Every objective opens a Run — the canonical unit of governed work. A run binds to a work item, thread, session, workspace, and project. Receipts, artifacts, and approvals are typed, cross-device shared truth.

The run contract is surface-neutral: Agents, CoWork, Code, Productivity, CLI, and any future surface are profiles over this contract, not parallel definitions. Models are replaceable; the contract is not.

NOME uses a three-tier state split for cross-device continuity:

Shared state — durable truth synced across all devices (threads, work items, receipts).

Soft state — last-writer-wins preferences like draft buffers and tab registries.

Per-device state — local-only data like viewport scroll position and transient UI state.

Object-based continuity is keyed to the active work item, with fail-closed restore and schema validation.

NOME dynamically routes each request to the right model based on workload characteristics, cost constraints, and latency requirements. Multiple aggregation strategies are available when high-stakes outputs benefit from comparison.

Effort budgets on each run prevent over-investment in simple queries and under-investment in complex ones. Cost tracking is a first-class run metric.

Offline runs use the same run contract as cloud runs. Tool invocations that cannot execute offline are queued as deferred tasks and resolve when connectivity returns.

Local model selection follows the compute policy and local model registry. Blackout is the dedicated native-first offline surface with zero network latency and total data privacy on Apple Silicon.