Skip to main content

Long-Term Memory

When you enable Long-Term Memory on a project, ORQO doesn't just store your content — it understands it. Every document, workflow result, and web capture is analyzed, classified, and woven into a knowledge graph that your agents can navigate like a structured library rather than a pile of text.

The key: ORQO's knowledge graph is built on a formal ontology — a scientific classification system that can semantically categorize any piece of knowledge, regardless of domain. Not ad-hoc tags. Not keyword matching. A peer-reviewed theory of how knowledge is structured.

This is fundamentally different from standard AI retrieval. Most platforms use RAG — Retrieval-Augmented Generation — which treats your documents as flat bags of text chunks and finds the most similar ones. Long-Term Memory goes further: it classifies every piece of content by what kind of knowledge it is, connects it through typed semantic relations, and lets agents traverse that structure.

Long-Term Memory overview

What Happens When You Enable It

Toggle Long-Term Memory on your project page, and three things start happening automatically:

  1. Document uploads are classified and added to the knowledge graph.
  2. Workflow results flagged as knowledge-worthy are captured and enriched.
  3. Web content captured by agents goes through the Knowledge Curator for evaluation before classification.

Your agents gain access to the QueryKnowledgeGraph tool — they can search, inspect, and navigate the graph through 11 structured directions.

Write a clear, specific project description — it guides the system on what topics matter and what to ignore.

Token Usage

Classifying content and building the knowledge graph requires LLM calls — every document that enters the system goes through a multi-pass classification pipeline that consumes tokens. This is why Long-Term Memory is a per-project setting, not a global default. Enable it on projects where structured knowledge accumulation adds real value, and keep it off for projects that don't need it.

The Knowledge Graph

Under the hood, Long-Term Memory is powered by a knowledge graph — a network of classified knowledge units connected by typed relations. This is what gives it structure and navigability.

Why Not Just RAG?

CapabilityStandard RAGORQO Long-Term Memory
RetrievalSimilarity search on embeddingsSimilarity search plus typed graph traversal
StructureFlat chunks, no relationships54 knowledge types across 4 epistemological classes
NavigationNone — each query is independent11 directions (deeper, broader, why, how, examples...)
RelationsNone or generic "related to"48 typed semantic relations (causal, hierarchical, temporal...)
ClassificationNone — content is what it isEvery unit classified by function: orient, explain, guide action, or reference
ContextLost between queriesPreserved through graph structure and concept containers

The Four Knowledge Classes

Every piece of content in the graph is classified into one of four fundamental classes. These represent the four ways humans use knowledge:

ClassFunctionExample
OrientationHelps you perceive and navigate a domainFacts, scenarios, overviews, problem statements
ExplanationHelps you understand why things are the way they areDefinitions, proofs, causal chains, arguments
ActionTells you how to do somethingProcedures, rules, checklists, strategies
ReferencePoints you to where information livesDocuments, archives, glossary entries, cross-references

These four classes branch into 54 specific knowledge types, each with precise classification criteria. The complete taxonomy comes from a formal theory of knowledge organization called the Web-Didaktik — see Web-Didaktik Ontology for the full breakdown.

How Content Gets Classified

When content enters the system, a three-pass pipeline transforms it from unstructured text into typed, connected graph nodes:

Content enters (document upload, workflow result, web capture)

Knowledge Curator evaluates and extracts substantive content

Pass 1 — Base classification: Orientation | Explanation | Action | Reference

Pass 2 — Sub-classification: full type path (e.g., Explanation:What:Definition:Term)

Pass 3 — Relation extraction: typed edges between units (CauseOf, Specializes, BasisFor...)

Knowledge units stored in the graph with embeddings and concept containers

See Classification Pipeline for the technical details.

How Agents Navigate Knowledge

Once content is in the graph, agents don't just search — they navigate. Starting from any knowledge unit, an agent can follow 11 structured directions:

DirectionWhat the agent is asking
deeper"Tell me more detail about this"
broader"What's the bigger picture?"
why"Why is this the case?"
consequences"What follows from this?"
how"How do I actually do this?"
examples"Show me a concrete case"
context"What surrounds this?"
related"What's connected to this?"
sources"Where can I read more?"
next / previous"What comes after / before?"

Each direction follows specific typed relations in the graph — "deeper" follows Specializes and PartOf edges, "why" follows CauseOf and BasisFor edges, and so on. This is what makes navigation meaningful rather than arbitrary.

See Knowledge Navigation for a deep dive.

Key Components

ComponentWhat it does
Web-Didaktik OntologyThe theoretical foundation: 4 knowledge classes, 54 types, 48 relation types, 11 navigation directions
Classification PipelineThree-pass LLM pipeline that classifies content and extracts relations
Knowledge NavigationHow agents traverse the graph using ontology-aware directions
Knowledge CuratorContent evaluation and routing — decides what's worth keeping

The Science Behind It

The knowledge graph is built on the Web-Didaktik ontology — a formal theory of knowledge organization developed by Prof. Dr. Norbert Meder (University of Bielefeld, 2006). This is not an ad-hoc categorization. It is grounded in decades of educational science research and was validated through the INTUITEL EU FP7 research project (Swertz et al., 2014).

The INTUITEL project demonstrated a key finding: using just four relation types, multiple distinct learning paths emerged naturally from a single knowledge domain — without any manual path authoring. The structure of typed relations was sufficient for meaningful navigation to appear on its own.

ORQO implements the full taxonomy of 48 relation types and operationalizes the theory using modern LLMs — solving what was previously the unsolvable "educated categorizer" problem. You used to need a domain expert to classify every piece of content. Now, LLMs handle this with over 94% agreement with human expert categorization.

Further Reading
  • Meder, N. (2006). Web-Didaktik: Eine neue Didaktik webbasierten, vernetzten Lernens. Bielefeld: Bertelsmann.
  • Swertz, C. et al. (2014). A Pedagogical Ontology as a Playground in Adaptive Elearning Environments. INTUITEL EU FP7 Project.