Speedway Technology · Atlas

Atlas Librarian is Speedway's segmented cognitive-memory engine.

Atlas Librarian provides the front-door memory authority for Atlas Lattice. Instead of treating memory as one undifferentiated vector of old text, the architecture classifies and routes knowledge into specialized cognitive segments, recalls only the subset relevant to the current task, tracks freshness and lifecycle state, and preserves project continuity across sessions and operational handovers.

17 canonical segmentsActive cognition, durable knowledge, governance, relationships, temporal memory and archive have distinct roles rather than sharing one generic store.
Selective and adaptive recallThe Conscious Memory Index keeps active context bounded; CMI v2 adds a state-aware evaluation path for deciding which eligible memories deserve that context.
Persistent project cognitionHandover, decisions, procedures, rules and event history help the project retain continuity beyond one conversation or one operator session.

The core idea

Memory should be routed by cognitive purpose, not merely stored because it existed.

A long-running operational system accumulates facts, decisions, procedures, incidents, identities, routes, schemas, preferences, deadlines and complete artefacts. Those things do not have the same meaning or lifecycle. Atlas Librarian gives each class an explicit role and lets the memory front door decide which segment should participate in a given recall.

Facts are not incidents

A durable project fact belongs in Semantic Memory; a specific observed outcome belongs in Episodic or Event Memory. Keeping that distinction reduces the risk of treating one historical occurrence as a current truth.

Decisions are not rules

Decision Memory preserves what was chosen and why. Rules Memory represents hard constraints and non-negotiable behaviour. The distinction matters when systems evolve.

Working context is not the archive

Working Memory stays intentionally small and active. Archive Memory preserves low-heat material for long-tail retrieval without crowding immediate reasoning.

Time is not just metadata

The Scheduler is a distinct temporal execution segment so a future condition, reminder or wake event can be represented differently from passive knowledge.

Whole artefacts need a staging lane

Scratch Pad is distinct from Working Memory because some reasoning depends on complete files, documents, images or structured objects rather than isolated excerpts.

Relationships are first-class context

Relationship Memory preserves links among entities, dependencies, causes and supersession chains so recall can expand through meaningful connections.

High-level cognitive flow

Observe, classify, route, retain, selectively recall and continue.

The public architecture can be understood as a governed sequence. The implementation deliberately separates fast active state from durable canonical memory, then promotes material into longer-lived segments when it warrants retention.

1. Memory candidate

An event, handover, project fact, procedure, decision, artefact or other memory candidate reaches the Librarian boundary with provenance and scope.

2. Classification and routing

The current implementation applies deterministic segment-aware classification and normalization. Explicit type and routing information can take precedence when the caller already knows the correct cognitive role.

3. Active or durable lane

Short-lived working context can remain in hot state, while durable knowledge is retained in the canonical memory layer with authority, freshness and lifecycle metadata.

4. Index-first recall

Recall begins by identifying the relevant segment and memory candidates rather than treating the full project history as one prompt-sized block.

5. Working set

The selected subset becomes active reasoning context. The architecture distinguishes memory that was merely retrieved from memory that was actually used.

6. Promotion and continuity

Important working material can be promoted into durable memory; cooled or superseded material can move toward archive while remaining traceable when explicitly needed.

Atlas Lattice

The Librarian is the memory front door inside a broader Atlas architecture.

Speedway refers to the cognitive memory layer as Atlas Lattice, with the Librarian acting as its Conscious Memory Index. The design goal is not to make memory itself the authority for protected business state. Atlas can remember and reason broadly while canonical Speedway services remain authoritative for orders, inventory, payments, identity, permissions and other deterministic records.

Memory authority

Atlas Librarian governs the meaning and lifecycle of Atlas memory. It can record which memory is authoritative within its memory domain and which items are contextual or historical.

Operational authority

Protected business state continues to resolve through the owning Speedway service, policy and permissions. Memory can explain that state without silently becoming a parallel ledger.

Bounded reasoning

This separation lets Atlas carry durable context across work while respecting the authority boundary described in Atlas AI Operations.

Implemented architecture versus evolution

The public technical record distinguishes established foundations, internal evaluation paths and future research.

As of 5 September 2026, the canonical 17-segment registry, deterministic segment-aware classification, hot-state versus durable-memory separation, freshness metadata, established fast recall, scheduler linkage and memory usage tracking remain concrete foundations. CMI v2 is now implemented as an additive internal evaluation path for state-aware, authority-aware, lifecycle-aware and context-budgeted recall; it has not silently replaced the established recall path.

Established foundation

Canonical segment roles; memory scopes and lifecycle states; thermal states; deterministic classification; index-oriented recall; hot working state; durable retention; scheduler-aware memory; usage and freshness tracking.

CMI v2 evaluation path

Adaptive candidate ranking, authority and risk sensitivity, supersession handling, temporal and continuation state, relationship signals, verified outcome evidence and bounded Working Memory assembly.

Read the CMI v2 record →

Still evolving

Broader graph traversal, longer-horizon consolidation, richer outcome learning and comparative external benchmark coverage remain development and evaluation areas rather than completed universal claims.

Deliberately undisclosed

Exact algorithms, weights, thresholds, private prompts, routing recipes, consolidation triggers, internal topology and other enabling or security-sensitive details are intentionally protected Speedway intellectual property.

Read the disclosure boundary →

Read the architecture

Nine documents establish the public Atlas Librarian technical and evidence corpus.

Adaptive Cognitive Recall

CMI v2 state-aware utility, verified outcome evidence and bounded context assembly.

Read about CMI v2 →

Canonical definition

Atlas Librarian is Speedway's segmented cognitive-memory engine for persistent, selective and governed project intelligence.