Bixel

KDB.AI

Kdb.ai
Company Overview

As of July 20, 2026: KDB.AI is a vector database targeting AI developers with a time series plus vector search combination that most pure-play vector stores do not offer.

The product lists 14 stated capabilities including sub-second latency, shape-based matching, and on-disk indexing, with 4 integrations covering LangChain, GitHub, Slack, and its parent Kdb ecosystem. The time series angle is the clearest differentiator in the positioning; whether it holds at scale is not independently verified here.

Medium confidence · 28 dated facts
Corroborated across 3 dimensions of the record.
integrations
4
Jul 2026
technologies
6
observed
dated changes
40
Aug 2025
The record, by dimensionevery dimension is its own page →
FeaturesHigh confidence · 18 dated facts
Corroborated across multiple dated, sourced facts.
Focused feature set
The 14 stated capabilities span real-time search, metadata filtering, multi-source retrieval, and shape-based matching, which is an unusual inclusion that suggests use cases in pattern detection on sequential data. LangChain is the only major third-party AI framework in the 4-integration list, so buyers building outside that ecosystem should check compatibility before committing.
Full features read →
Stack
6 detected
The live site runs on WordPress and Nginx with Google Analytics, Google Tag Manager, YouTube, and OneTrust detected, which is a standard marketing-site stack and says nothing about the database infrastructure itself. Buyers evaluating the product should not read the site stack as indicative of what runs underneath the data layer.
High confidence · 6 dated facts
Corroborated across multiple dated, sourced facts.Full read →
Positioning
Vector Database
The homepage headline "The Scalable Vector Database for AI" is a direct pitch to AI developers, and the sub-headline explicitly calls out contextual search, time series search, and mixing structured with unstructured data. That last point is the most specific claim on the page and is the one worth pressure-testing in a proof of concept.
High confidence · 4 dated facts
Corroborated across multiple dated, sourced facts.Full read →
Change History40 dated events on the record
Feature added: Temporal Similarity Search
Feature removed: Semantic Search · high significance
Positioning changed: Target Segment
Feature removed: Temporal Search · high significance
Feature removed: Youtube · high significance
Feature removed: Llamaindex · high significance
Feature removed: Unstructured IO · high significance
Get this record via API / MCPevery field dated and sourced
RESTopen tier
GET https://api.bixel.com/v1/companies/kdb.ai

{
  "data": {
    "company": {
      "name": "KDB.AI",
      "domain": "kdb.ai",
      "categories": [
        "vector-databases"
      ]
    },
    "dimensions": {
      "stack": {
        "facts": [
          {
            "key": "stack.tech.wordpress",
            "value": true,
            "provenance": "observed",
            "as_of": "2026-07-20",
            "source_url": "kdb.ai"
          }
        ]
      },
      "…": "…"
    }
  }
}
MCPfor agents
# any MCP client (Claude, agents)
const record = await bixel.get_company({ domain: "kdb.ai" })

# returns the whole 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.
How Bixel reads this

Every read above is derived from public signals, each sourced and dated, and kept honest about provenance: what the company states on its own pages and job posts (pricing, security, careers, positioning, its backend stack) versus what Bixel independently detects (technologies, infrastructure). Where a stated claim is also detected we mark it verified; where we only have the claim, we say so. Bixel infers posture: how it monetizes, how mature it is, where it's heading. It does notclaim private financials it can't observe. Where signals are thin, the confidence says so.

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