Get Started

Neural world models simulate how the world evolves under actions. ArcFlow records what actually happened. These are different tools for different jobs — simulation in the neural tier, persistence here.

ArcFlow is the blazing-fast graph engine for modeling the real world. A persistent, spatially indexed, temporally versioned, confidence-scored store of actual world state — exact, queryable in microseconds, running in-process alongside whatever generates the data. The operational world model layer of your stack.

Eight engines under one query language. Graph storage, query execution, live streaming views, an event bus, a behavior engine, an algorithm library, durability, and language bindings — pre-integrated, designed from scratch for spatial-temporal workloads. One ISO GQL dialect describes the schema, the query, the live view, the trigger, and the algorithm call. The coherence is the product; the sub-millisecond latency is the consequence of not assembling stacks.

MATCH (s:Sensor)-[d:DETECTED]->(r:Robot)-[:OCCUPIES]->(z:Zone)
WHERE d.confidence >= 0.90 AND z.hazard > 0.15 AND r.battery < 30
RETURN r.name, z.name, avg(s.reliability * d.confidence) AS trust

Deterministic. Against exact history. ArcFlow tells you what did happen — which sensor, which detection, what confidence, which zone, at any moment in the past — with one query.

The AI infrastructure stack has three tiers. Foundation models handle language and perception. Neural world models simulate how the world evolves under actions. ArcFlow is the persistence tier — the layer where actual world state lives, versioned, spatially indexed, confidence-scored, queryable.

It runs in-process — no server, no network hop, no inference cluster. Co-located with the agent, robot, or vehicle that needs it. For any real-time control loop, in-process execution is an architectural requirement, not a convenience.

Every mutation is versioned via ArcFlow Clock Domains — each source advances at its own rate, the world model merges them. Every fact is graded by the ArcFlow Evidence Model — observation class (observed, inferred, predicted), confidence score, and provenance chain are storage primitives, not optional annotations. The full history is queryable with ISO GQL.

Try instantly — zero install#

Open ArcFlow Engine in your browser. Paste any GQL query — persistent storage, no install, no signup.

CREATE (e:Entity {id: 'unit-01', x: 12.4, y: 8.7, _observation_class: 'observed', _confidence: 0.94})
CREATE (e:Entity {id: 'contact-x', x: 80.0, y: 90.0, _observation_class: 'predicted', _confidence: 0.38})
CALL algo.nearestNodes(point({x: 0, y: 0}), 'Entity', 5) YIELD node, distance RETURN node.id, distance
MATCH (e:Entity) WHERE e._confidence > 0.8 RETURN e.id, e.x, e.y
MATCH (e:Entity) AS OF seq 1 RETURN e.id, e._confidence

Install#

curl -fsSL https://staging.oz.com/install/arcflow | sh

Then:

arcflow --playground

All paths#

The full install matrix — every binding, with current shipping status — is on the Installation page. It is generated from the engine's release manifest, so what you see is what is actually published.

For the impatient:

• Browser — zero install, click and go.
• CLI (coding agents) — once installed, arcflow query '...'.
• MCP (cloud chat UIs) — npx arcflow-mcp.

Next#

• Quickstart — first world model query, step by step
• Installation — all install methods in detail
• Project Setup — Express, testing, monorepo

Guides#

• Building a World Model — entities in space, temporal memory, live monitoring
• Swarm & Multi-Agent — shared world model as coordination substrate for AI agent swarms
• Trusted RAG — confidence-filtered retrieval, graph context, vector + graph + full-text
• Agent Integration — CLI binary, MCP, and napi-rs — which surface fits your execution context
• Data Quality — live DQ, batch==delta equivalence, pipeline integrity
• Code Intelligence — queryable codebase graph for coding agents

Use cases#

• Autonomous Systems — robot fleets and UAV coordination on a shared world model
• Digital Twins — live spatial replica of physical facilities
• Robotics & Perception — sensor fusion, track lifecycle, ROS bridge