START HERE → The Intelligent Graph is the bridgework. The movement it serves is The Collaboration Paradigm — read that first.
Ontology · relationships come first

First Citizen

In graphs today, a relationship is at best a first-class citizen — a real object beside the nodes. That isn't far enough. A relationship isn't one citizen among equals; it is the First Citizen — and it doesn't just describe the world, it executes it.

A cellular-sheaf diagram over a graph — structure carrying meaning on every node and edge.
Forty years on one conviction: relationships come first.

What it is

Bridgework, not a building.

The Intelligent Graph is the bridgework that carries the Collaboration Paradigm into implementation — the span from an idea about how intelligence collaborates to a substrate where it actually can.

Architecture gives you a place to move into — rooms, walls, a platform you're then stuck on. Bridgework is different. You don't sit inside a bridge; you connect to it, cross it, and extend it. TIG is a gateway, not a destination — relationship-first infrastructure your people, models, and agents connect to, traverse, and build onward from. Not a walled platform you're locked into; a span you cross.

A bridge is a relationship made traversable.

Begin with being

The First Citizen.

Relationships in graphs today are treated two ways. In the RDF stack, they're buried inside predicates. In Neo4j, they're promoted to first-class citizens: real objects, with identity and properties of their own.

Building from the original definition of ontology: nothing exists until the very concept of existence exists — something exists, OR it doesn't. You need the OR before the thing. To exist is to be an element of a set, and membership is that OR — in, or out. The distinction comes first, and a distinction is a relation.

So relationships are not just first-class citizens. They are the First Citizen.

Relationships realize entities. Realization is an action. A relationship isn't glue between two real things — it is what makes them real, and a thing that does. Reticulation, not reification.

More than declaring relationships, more than recording activities — relationships execute. Recording is history. Execution is now. A graph that remembers tells you why the agent failed, after it failed. A graph whose relationships execute keeps it from failing in the first place. Not the agent's memory. The agent itself.

Vector to the mathematics

From philosophy to a sheaf.

Inference — derive what follows from what's said — is only the first floor. An operation's order is the order of structure it reaches over:

order 1 · Infer
reaches over elementswhat follows.
order 2 · Compute
reaches over the whole topologywhat the structure reveals. Centrality, community, similarity: the graph reasons about itself.
order 3 · Reticulate
reaches over whole spaceswhat relates across worlds.
order ω · Interact
reaches over universes and the intelligences reading themwhat emerges in conversation.
The object that makes this rigorous

Model the graph as a cellular sheaf: data on every node and edge, with rules for how they must agree. A view becomes a section; consistency becomes cohomologyH⁰ is what holds together (knowledge), is the contradiction that can't (the obstruction). Grounding is driving H¹ toward zero.

The full consistency engine is the direction, not a shipped feature — we build toward it in the open. Read the math →

A graph whose nodes and edges carry fibers, with H⁰ and H¹ chalked — a cellular sheaf.
A view becomes a section; consistency becomes cohomology — H⁰ what holds, H¹ what doesn't.

What this lets us build

The graph your extractor throws away.

Your LLM pipeline extracts a rich graph of concepts and how they relate — then your tools show almost none of it. A renderer only draws an edge when both endpoints are nodes, so the conceptual half — the ideas and how they connect — is never rendered, never traversed, never queried. The Intelligent Graph recovers that discarded layer as a non-destructive overlay, grounds it, and lets you act on it.

Run this on your own graph: count the edges whose endpoint isn't a node. That number is the graph you're throwing away. In our pilot, it was the large majority of the relationship layer.

What it does

Recover, ground, and act.

01Recover

Read the source read-only; surface the relationships it extracted but couldn't display.

02Ground

Type each raw relationship into a traversable graph — keeping the original string, so re-typing later is a single traversal, not a re-import.

03Act

Hitting a relationship can do something, not just return a row. The graph stops being a place you store knowledge and becomes one that executes.

Provenance is a property, not a supernode. Every step is reversible by construction. We attach to your graph; we never restructure it.

Why it's different

From a model to an engine.

Relationships first
Edges carry their own structure and behavior — no reification, no blank-node workarounds. The thing the semantic web couldn't do cleanly, done natively.
Executable traversal
Behavior binds to the kind of relationship you traverse. Inference becomes one behavior, not the whole paradigm.
Persistence
TIG carries structure and decisions across runs, so a re-import shows only what's new. Memory in service of action — not the agent reduced to its memory.
Reticulation
A two-way weave: TIG curates, then feeds interpretations back so the source's agents get smarter each cycle.

The register ladder

One idea, three registers — bridged.

The point of bridgework is that it connects. Every concept has a word an executive can use, a word the graph implements, and a word the mathematics proves — and they map cleanly onto one another. The Intelligent Graph is the middle rung: the representational bridge between the everyday and the formal.

Colloquial · Professional Representational · TIG Mathematical · Formal
ParticipantNode / EntityObject / Element
StewardCurator / GovernorObserver / Constraint
CommunitySector / ScopeGroup / Subspace
Collaboration SpaceGraph SpaceManifold / Topology
RelationshipEdge / ContractRelation / Morphism
BridgeTraversable EdgeMapping / Functor
RepresentativeView / ProjectionSection
FoldIdentity MergeQuotient / Equivalence
ReticulateStructure FormationSheaf Gluing
TraversalPathComposition

A bridge is a relationship made traversable; an edge, a relationship made representational; a morphism, a relationship made formal.

TIG + Solstone

Capture-to-graph, in a single self-contained stack.

The Intelligent Graph pairs with Solstone — Jeremie Miller's local-first memory platform — to turn a passive capture stream into a structured, queryable, annotatable graph. Sol captures and extracts; TIG recovers the discarded relationship layer, makes it traversable, and feeds curated interpretations back. Built for teams who want their own graph, on their own machine — not a hyperscale deployment.

Open core

An open core, with a commercial layer for the parts that act.

The core will be open source (Apache 2.0) — we're building it in the open. A commercial layer adds the operational and agentic capabilities teams pay for.

Who's behind it

One unbroken conviction: relationships come first.

Built by Michael Bauer — a 35-year through-line from rule-based expert systems to a billion-node production graph. → michaelbauer.com

Featured at Neo4j NODES 2026, with Solstone: "The Graph Your Extractor Throws Away."