Overview

Spectron stores authoritative and experiential material in one SurrealDB graph — the Authoritative and Experiential pillars from Eight pillars and six categories. This section is organised by what you do (ingest, retrieve, reason, tune), not by two separate products.

• Authoritative — manuals, policies, product data, structured uploads (source.kind = "document", higher default trust).

• Experiential — conversation, sessions, and derived facts (source.kind = "turn", reflections, elaborations, consolidations).

Start with Unified substrate and authority and Memory categories (the six experiential types, including chat-extracted knowledge — distinct from authoritative uploads).

Ingest

Authoritative

• Uploading documents, Bulk import

• Multi-modal content, Knowledge nodes

Experiential

• Remember — POST /facts and /facts/batch

• Sessions — containers for turns (creating, adding turns)

Retrieve

Unified read path over facts and document passages:

• Recalling memories — /query, /context, /chat

• Hybrid search, Keywords and BM25, Graph traversal

HTTP tables: REST API and Surface, models, and security.

Reasoning

How writes are extracted, reconciled, and time-stamped — for both documents and turns:

• Extraction pipeline

• Reconciliation and supersession

• Authority when pillars meet, Cross-layer linking

• Temporal validity, Instructions and uncertainties

Operations & tuning

• Reflect, Forget, Profiles

• Models per stage, Caching and invalidation, Ontology grounding