The world's power system, as one queryable graph.

The facts are public. The connections are the product.

Grid headroom, interconnection queues, ownership chains, water risk — the cross-domain question behind a siting or investment decision, answered in one sourced query instead of weeks of joining datasets.

Book a pilot See the live globe Explore the API

Fastest start: bring a siting shortlist — we re-rank it against the graph, live, on the first call.

Deterministic graph + SQL · no LLM · 10M+ nodes, 27M+ edges · every field sourced & dated

One query, one traversal5 domains

? Where can a 300 MW load contract clean-firm power?

scan →grid zonewholesale price, fuel mix, headroom
nearest_substation →substationinterconnection point & corridor capacity
located_in ←generatorsclean-firm capacity within reach
operated_by → parent →counterpartyresolved owner, group concentration
overlay →queue + watercongestion, completion history, stress
answerzones ranked, with the evidence attached src EIA · ENTSO-E · GLEIF · queuesfreshness per sourceconfidence tiered

Illustrative traversal — every hop is a real edge type; run it live from /docs.

Kortex is an API for energy and infrastructure due diligence. It connects assets, grid capacity, prices, interconnection queues, ownership, water risk and geopolitical exposure into one source-traceable graph. Use it to screen sites, counterparties, portfolios and grid constraints in minutes instead of weeks.

No LLM in the stack. Kortex is purely empirical data and deterministic graph traversal. Every result is reproducible, auditable, and traceable to named source datasets. There is no generative AI, no probabilistic inference, and no black-box scoring. What you query is what the data says.

Screening and signal generation tool, not a forecasting platform. Kortex surfaces current-state compound risk, competitive dynamics, and structural exposures from historical and real-time data. It does not produce forward price curves, demand forecasts, or scenario models. It is designed to complement forecast-oriented research platforms, not replace them.

10M+ nodes 27M+ edges 521 PostGIS tables 2.02B rows 46 node types 58 edge types 16 schema domains $2.05T revenue modelled · 16,320 operator groups

Questions Kortex is built to answer

Worked results below were verified against the linked endpoints as of the 2026-07-08 snapshot. The graph refreshes continuously, so figures drift between snapshots — the endpoints always return current values with source provenance.

Which utilities show the lowest queue completion while earning billions from fossil plants in the same grid zones?
Traverses: LBNL queue completion data × generator revenue × corporate ownership × grid topology.
Result: Southern Company has a 1.5% queue completion rate (9 of 803 projects built since 2015) while earning $7.2B/yr from fossil generators in the same grid zones. FERC Order 2023 queue clearance threatens $9.4B/yr across the 15 utilities with the highest unresolved queue concentration.

Where should a data centre site for cheapest clean power?
Traverses: wholesale prices × generation fuel mix × queue pipeline × grid capacity × climate risk.
Result: Norway NO4 at $21/MWh, 1% dirty share, 600MW available capacity.

Which operators claim clean energy but earn over 90% revenue from fossil?
Traverses: generator fuel type × 3-layer revenue model × GLEIF corporate hierarchy × entity resolution.
Result: a ranked operator list with the fossil/clean revenue split per operator — every row traceable to its source data and testable against public filings.

The graph, up close

One real node and its first-hop neighbourhood — a 9.5 GW gas plant in Dubai. Every edge is typed and carries its fidelity: how the connection was established, from authoritative topology down to spatial inference. This record, its neighbours, and every field's source are what the API returns.

authoritative — topology / point-in-polygon derived — computed join inferred — spatial proximity stitched — curated entity resolution

A real record: generator oim_gen_592115432 and its typed edges. Each edge carries method, confidence and audit status; each field carries source, method and as-of date.

Revenue model methodology

Three-layer empirical model with explicit confidence tiers.

Layer 1: Generation revenue. Per-generator output (capacity × fuel-specific capacity factor) × grid-zone wholesale price (empirical: ENTSO-E, EIA, AEMO, or IEA/EIA benchmarks where hourly data unavailable). Covers $2.19T across 210K generators.

Layer 2: Network revenue. Per-substation share of grid-zone T&D revenue (retail price minus wholesale price × zonal demand ÷ substation count). Covers $1.17T across 734K substations.

Layer 3: Retail revenue. Country-level retail electricity revenue from World Bank / IEA. $3.36T globally — consistent with IEA estimates (~3.1% of global GDP).

Layers are additive where data permits, with revenue tier flags: tier_1 (empirical hourly prices, highest confidence), tier_2 (country-level benchmarks), tier_3 (modelled from regional proxies).

Revenue figures are modelled screening estimates for relative comparison — not audited financial revenue, and not suitable as valuation input without independent verification against operator filings.

Entity resolution uses GLEIF LEI matching (3.3M entities) with manual curation (134 corporate group mappings, 25+ groups). Revenue consolidates across subsidiaries to ultimate parent. All source data, matching methodology, and confidence tiers are queryable via the API.

Coverage

Ten domains feed the graph — energy generation and transmission, corporate ownership (GLEIF, SEC, ICIJ), hourly electricity markets, climate and water risk, geopolitics, economics, interconnection queues, the nuclear fuel cycle, digital infrastructure, and maritime movement. Depth is deepest in the US, Europe and Australia (hourly market data) and tiered elsewhere; refresh cadence runs from 5-minute feeds to annual registries, per source. Every source, licence and cadence is listed on the Sources page; the full machine-readable structure is at Schema.

What Kortex is — and what it is not

Kortex is	Kortex is not
Cross-domain graph traversal — ownership chains, grid topology, water basins, queues and sanctions exposure connected as one queryable graph. This is the differentiator.	A forecasting platform. No forward price curves, no 30-year scenarios, no demand projections.
Pre-built compound-risk screens (water × carbon × queue × ownership) that resolve in seconds instead of weeks of manual dataset assembly.	Analyst commentary or sector opinion. Kortex returns data and query results, not narratives.
End-to-end entity resolution — GLEIF LEI matching with curated review connects 210K generators to corporate ownership and revenue.	A ratings product. No composite ESG scores, no black-box weightings — the underlying fields and their sources are always exposed.
Depth where it matters — 4.3B wholesale price rows across 53 TSOs, interconnection-queue completion by utility and technology, ICIJ offshore-leaks integration for adverse-entity screening.	A terminal. Kortex is API-first: native REST plus read-only Cypher graph queries, built to be consumed by code and by AI agents.
Transparent about maturity — an early-stage product from Orkora Ltd, sold founder-led with pilot programmes.	A replacement for established research subscriptions. Kortex is designed to sit alongside them as the quantitative screening layer.

Positioning: research platforms sell forecasts and analyst expertise. Kortex sells the connective tissue between public datasets — a purely quantitative, programmable screening layer that complements existing subscriptions rather than replacing them.

The API

One typed, self-describing REST API in four layers: Insights (pre-built cross-domain screens — stranded assets, queue blockage, fossil-revenue exposure, compound vulnerability), Graph (search, N-hop traversal, read-only Cypher over the full graph), Time series (4.3B price rows across 53 TSOs, generation, demand, interchange) and Reference (taxonomies and the complete data register). Machine-readable OpenAPI, an MCP server for AI agents, and per-query cost in the response. Full reference at /docs.

Who it is for

User	What they use it for
Data-centre & load siting teams	Grid zones ranked by clean-firm availability, queue congestion, headroom, water stress and counterparty exposure — before committing development capital.
Infrastructure funds & lenders	Pre-diligence screening of assets and counterparties: transition exposure, stranded-asset risk, physical risk, ownership-chain concentration.
Grid & energy consultancies	Cross-engagement data infrastructure: market entry, queue assessment, retirement screening — without rebuilding the joins per project.

The same graph also serves development finance, ESG and transition-risk analysis, commodity desks, and AI agents via the MCP surface — ask us about your workflow.

Quick start

The three "try live" queries below run against the production graph with no key — rate-limited, exact queries only. Full parameter access comes with an API key.

Global Viewer — the graph on a live globe Data Sources & Licences Schema Atlas Interactive API Docs (Swagger) API Reference (ReDoc) Platform Statistics Try live: queue completion Try live: fossil revenue exposure Try live: top grid zones

Contact

Orkora Ltd · kortex@orkora.com · API access by agreement

Pilot programmes available. We recommend a technical demo session where we run Kortex queries against assets or regions you already know well, so you can validate outputs against your existing data.