Bixel

KDB.AI

KX Software Limited·Kdb.ai
Product Capabilities

Hybrid search platform

As of September 3, 2026, KDB.AI's features: 11 stated capabilities covering hybrid search and multi-tenancy give enterprise buyers a reasonable checklist, but one listed integration means most connection work lands on the buyer's engineering team.

Backed by 12 dated facts
Every value derives from a dated, sourced capture — open any fact for its source.
Capabilities
ExplainabilityHybrid SearchMulti ModalMulti Source RetrievalMulti TenancyNatural Language InterfaceOn Disk IndexingReal Time SearchTemporal Similarity SearchTime SeriesVector Search
Integrations
Langchain
Features Change Historydated events · values unlock with a key
Feature removed: Metadata Filtering · high significance
Feature removed: RAG · high significance
Feature removed: Shape Based Matching · high significance
Feature removed: Sub Second Latency · high significance
Feature removed: Vector Indexing · high significance
Feature added: Explainability
Feature added: Hybrid Search
Feature added: Natural Language Interface
Every features fact on this pagekey · value · provenance · dated · sourced
FactValueProvenanceAs ofSource
features.explainabilityExplainabilitycompany stated2026-09-03kdb.ai/solutions
features.hybrid-searchHybrid Searchcompany stated2026-09-03kdb.ai/learning-hub
features.integration.langchainLangchaincompany stated2026-09-03kdb.ai/learning-hub
features.multi-modalMulti Modalcompany stated2026-09-03kdb.ai/learning-hub
features.multi-source-retrievalMulti Source Retrievalcompany stated2026-09-03kdb.ai/solutions
features.multi-tenancyMulti Tenancycompany stated2026-09-03kdb.ai/legal/
features.natural-language-interfaceNatural Language Interfacecompany stated2026-09-03kdb.ai/solutions
features.on-disk-indexingOn Disk Indexingcompany stated2026-09-03kdb.ai/learning-hub
features.real-time-searchReal Time Searchcompany stated2026-09-03kdb.ai/solutions
features.temporal-similarity-searchTemporal Similarity Searchcompany stated2026-09-03kdb.ai/learning-hub
features.time-seriesTime Seriescompany stated2026-09-03kdb.ai/solutions
features.vector-searchVector Searchcompany stated2026-09-03kdb.ai/solutions
Features across Vector DatabasesKDB.AI ranked in place · tap through for each read
CompanyFeatures readFacts
ZillizHybrid search platform75
WeaviateHybrid search platform35
ChromaHybrid search platform34
QdrantFocused feature set32
VectaraAgentic RAG platform31
LanceDBHybrid search platform25
PineconeReranking platform23
ActiveloopFocused feature set16
EpsillaMulti-tenancy platform14
KDB.AI this recordHybrid search platform12
TopKHybrid search platform10
VespaHybrid search platform10
TurbopufferMulti-tenancy platform9

No observed features facts yet for Marqo, Milvus and MyScale.

Get features for kdb.ai via API / MCPevery field dated and sourced
RESTopen tier
GET https://api.bixel.com/v1/companies/kdb.ai/facts?dimension=features

{
  "data": {
    "facts": [
      {
        "key": "features.explainability",
        "value": true,
        "provenance": "company_stated",
        "as_of": "2026-09-03",
        "source_url": "kdb.ai/solutions"
      },
      {
        "key": "features.hybrid-search",
        "value": true,
        "provenance": "company_stated",
        "as_of": "2026-09-03",
        "source_url": "kdb.ai/learning-hub"
      },
      {
        "key": "features.integration.langchain",
        "value": true,
        "provenance": "company_stated",
        "as_of": "2026-09-03",
        "source_url": "kdb.ai/learning-hub"
      },
      {
        "key": "features.multi-modal",
        "value": true,
        "provenance": "company_stated",
        "as_of": "2026-09-03",
        "source_url": "kdb.ai/learning-hub"
      },
      "…"
    ]
  }
}
MCPfor agents
# any MCP client (Claude, agents)
const record = await bixel.get_company_facts({ domain: "kdb.ai", dimension: "features" })

# returns the features record above,
# each value with its source_url + as_of,
# ready to reason over
Build on the company record. One key, REST + MCP, every signal dated and sourced back to the page it came from.

Public record, read from companies' own pages and boards. Every fact dated and sourced; provenance (observed vs company stated) shown inline.