---
title: "kdbai-knowledge"
description: "KDB.AI vector database: schema design, hybrid search, integration patterns, and vector-index sizing"
canonical: https://agentpluginsdirectory.com/plugins/kdbai-knowledge
last-updated: 2026-10-18
---

# kdbai-knowledge
KDB.AI vector database: schema design, hybrid search, integration patterns, and vector-index sizing
- Slug: kdbai-knowledge
- Publisher: KX
- Repository: https://github.com/KxSystems/kx-skills
- Manifest: plugins/kdbai-knowledge/plugin.json
- Version: 0.3.0
- Category (editorial): databases
- Skills: 2 (kdbai, sizing)
- MCP servers: 1 (kx-docs-mcp)
- Stars: 21
- Repository created: 2026-05-20
- Repository last pushed: 2026-10-15
- Publisher type: Organization
- Listing: https://agentpluginsdirectory.com/plugins/kdbai-knowledge
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## Skills

- kdbai: Use when building vector search, RAG pipelines, hybrid search, time-series pattern matching, or managing tables in KDB.AI. Also use when asked about kdbai_client, similarity search, reranking, KDB.AI filters, or CAGRA GPU indexes.
- sizing: Guide KDB.AI sizing, capacity planning, and server resource configuration by collecting dataset and usage requirements, recommending suitable vector indexes and starting configurations, and estimating RAM, GPU VRAM, and persisted disk. Use for KDB.AI hardware requirements, capacity planning, memory…

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.

## MCP servers

- kx-docs-mcp: transport: streamable-http; url: https://kx2.mcp.kapa.ai

Read from the plugin's own mcp.json. Environment variable names only, never values.