KLOOM
Book a demo
PLATFORM
Morphic Identity EngineImmutable Evidence APIPoint-in-Time InvestigationsAgent Identity Layer
SOLUTIONS — BY INDUSTRY
National Security & IntelFinancial Intelligence & BankingCrypto & Web3 Compliance
BY MISSION
Sanctions & SDN ScreeningAdverse Media MonitoringOSINT Subject ResolutionContinuous Due Diligence & KYC
COMPANY
CareersContact
Book a demo
The identity layer for AI

Truth is uncertain. Kloom is the graph that keeps it that way.

Kloom is a probabilistic knowledge graph for entity resolution. Instead of binary matches at ingest, it holds the evidence, scores the alternatives, and resolves identity per query — so false positives don’t compound and false negatives don’t hide. The same mention can be a match in one context and not in another. That’s the point.

Book a demo
3 MENTIONS · 1 PERSON ENTITY3 MENTIONS · 1 ORG ENTITYTYPED, CONFIDENCE-WEIGHTED EDGES“Andrey Volkov”“Андрей Волков”“A. Volkov”PERSON“Lumen Reserve”“Люмен Резерв”“Lumen Reserve LP”ORGANIZATIONfounder_of · 0.71CEO_of · 0.92
01 · The shape of the problem

Identity isn’t in any one document.
It’s scattered across all of them.

Three sources mention “Lumen Reserve.” Same company? Different companies? One of them sanctioned, the other not? The evidence is genuinely underdetermined — there is no string match, no rule, no LLM prompt that can resolve it from inside any single document.

Most pipelines force a binary answer at ingest. Kloom holds the evidence, scores the alternatives, and lets your workflow ask the identity question when it actually has the evidence to answer it.

three mentions, three sources, one open question
01
OFAC SDN · 2024-03-04
Lumen Reserve” — designated entity. Sector: financial services. Jurisdiction listed as Cyprus.
02
Companies House · 2019-08-22
Lumen Reserve LP” — limited partnership incorporated 2019. Registered office: London, UK.
03
FT archive · 2025-04-11
Lumen Reserve, the Eastern-European investment vehicle founded by Andrey Volkov, announced…”
One entity? Two? Three?
02 · What a probabilistic knowledge graph adds

Three primitives.
One live graph.

A PKG isn’t a smarter database — it’s a different kind of object. One that reasons about identity, holds typed relationships through time, and stays live under the workflows querying it.

01

Identity reasoning

“Lumen”“Люмен”“Lumen LP”

Probabilistic merging of mentions into entities — with confident identity, confident distinction, and genuine underdetermination held as three distinct states. No premature collapse.

outcome
Defensible identity decisions in regulated workflows.
02

Relationship & temporal reasoning

CEO_ofPERSONORG

Typed, directional, confidence-weighted relationships between entities. Attributes carry temporal bounds — what was true, when, and how sure we are.

outcome
Network analysis and historical reconstruction across messy corpora.
03

Live querying & alerting

QUERY

PKG-QL standing queries running against the live graph. Subscribe to a mission; receive alerts the moment the evidence changes.

outcome
Search becomes monitoring. Investigative footprint compounds.
03 · The platform

One probabilistic knowledge graph.
Engineered from the ground up.

The PKG is the product — a four-layer graph that reasons about identity probabilistically. The work that makes it trustworthy happens beneath the surface: scoring matches, preserving evidence, and versioning every mutation so a query made today can be defended a year from now.

core platform

Probabilistic Knowledge Graph

A four-layer graph — evidence, graph, cluster, curated backbone — that reasons about identity probabilistically. Resolve entities at query time under your own merge policy. Traverse typed relationships. Pin a session to a graph version so your workflow doesn’t shift under you mid-investigation.

entity resolution typed relationships predicate registry session pinning air-gap deployable
tsconst entities = await pkg.query({
  pkgql: `MATCH (e:Entity {name: 'Lumen'})
                 (company:Entity)
             WHERE (e)-[:trades_with]->(company)
             AND company.sanctioned = true
           WITH PROBABILISTIC MERGE THRESHOLD 0.5
           RETURN e, company`,
  session_id,
});

// each entity carries:
//   identity_distribution[]
//   known_names[]  (original script)
//   corroborated_attributes[]
//   evidence_sources[]
powered by

Morphic Identity

Identity is stored as an evolving state, not a static fact. As new data is ingested, your view of it stays up to date.

Evidence layer

Raw mentions are never discarded. Every entity claim points back to the document and passage that produced it.

Sessions & audit

Queries pin to a graph version for the lifetime of a workflow. Every mutation is recorded with the acting principal.

04 · What we commit to

Six commitments, end to end.

Probabilistic
Interpretable
AعMulticultural
Auditable
Sourced
Sovereign
05 · Built for

Designed for teams that can’t afford a false negative.

Financial sector

AML, KYC, and sanctions teams at banks, payment processors, and crypto compliance shops. Replace four rule-based tools with one evidence-backed platform.

  • AML transaction monitoring
  • KYC onboarding
  • PEP / RCA screening
  • Crypto compliance
  • Correspondent-banking review

National security

Watch-list maintenance, sanctions screening, OSINT entity resolution, intelligence-context due diligence. The systems that ingest a million mentions a week and must defend every entity decision.

  • OSINT subject resolution
  • Watch-list / target-deck maintenance
  • Cross-source intelligence fusion
  • Threat-network mapping
  • Foreign-influence and disinformation tracking
06 · Deployment posture

Sovereign by design.

Identity work for national-security and FI customers can’t be outsourced to a vendor’s cloud. Kloom is a library you operate inside your perimeter, with the data flows you require.

Air-gap deployable

Sovereign, integrator-owned, no phone-home. Runs on hardware-limited environments by design.

Replayable audit log

Every mutation — resolutions, anchor confirmations, predicate registrations — recorded with the acting principal.

Evidence preserved

Raw mentions are never discarded. Every entity claim points back to the document and passage that produced it.

Original-script storage

Names are indexed in the script and language in which they arrive. No lossy index-time translation.

Ready when you are

Bring your messy evidence.
We’ll show you the entities your current stack misses.

A demo runs against representative data from your domain and returns the resolved entities you can audit end to end. Thirty minutes, with engineering in the room.

Book a demo