Map processes. Build a governed knowledge graph. Run it on your own infrastructure.

Connect your systems, review what gets extracted, govern it with a versioned ontology, and explore it through process maps, business rules, and a grounded chat assistant -- deployed as one stack, on infrastructure you already control.

How data moves through the system

Every stage is a real, reviewable step. Nothing reaches your knowledge graph without a human approving it first.

STEP 1

Connect

GitHub, Confluence, NetSuite, S3, or a manual upload.

STEP 2

Review & govern

Every document moves through Raw → Workspace → Canonical with a human at each layer, against a versioned, business-editable ontology.

STEP 3

Understand

An approved knowledge graph in Neo4j, drawn as process maps with business rules that each cite a real source. Never fabricated, always traceable to the document it came from.

STEP 4

Ask & act

A chat assistant grounded in your graph that cites what it used, and read-only access for your own agents over REST, MCP or SQL.

What’s inside

Every capability below is real and runnable today. Not a roadmap slide.

Connectors

Incremental sync from GitHub, Confluence, NetSuite, and S3, with every item staged for review before it enters the Vault.

Document Vault

Three-layer moderation (Raw → Workspace → Canonical) with full version history, and a human approval before anything reaches the graph.

Ontology Studio

A versioned, business-editable schema. Describe your business in plain language, import a DDL or YAML data model, and approve every change as a proposal.

Process maps & rules

Maps drawn directly from promoted graph data, with business rules that each cite a real source. Export as PDF, picture, or Mermaid.

Knowledge Graph

Reviewed entities and relationships in Neo4j, browsable by business area as a graph, a table, or written insights. Only approved facts are visible downstream.

Company Brain

Hybrid retrieval (vector + full-text) over your own graph, with citations checked against what was actually retrieved. Never an unsourced answer.

Review & feedback

Submit feedback with attachments and track it from Submitted to Reviewed, Implemented, and Approved, with a Final page of approved results.

Agent tools + MCP

A read-only query surface over the graph, exposed as REST endpoints, a real MCP server for Claude Desktop, Cursor, and other MCP clients, and a read-only SQL role.

Sign in to your workspace

Your team’s connectors, ontology, and knowledge graph are already waiting.