Which embedding models are compatible with this skill?

It supports any embedding model, with built-in presets for OpenAI ada-002 (1536 dimensions), sentence-transformers (768), and all-MiniLM-L6-v2 (384).

How fast is AgentDB Vector Search compared to other databases?

AgentDB is optimized for extreme performance, delivering operations 150x to 12,500x faster than traditional vector solutions, with search latencies often falling under 100 microseconds.

What is the benefit of using quantization in AgentDB?

Quantization significantly reduces the memory footprint of your vector database. For example, Binary Quantization can provide a 32x reduction, allowing you to store millions of vectors with minimal RAM usage.

Can I use AgentDB Vector Search directly in Claude Code?

Yes, it includes an MCP server integration that allows you to use tools like agentdb_query and agentdb_store directly within your Claude Code terminal sessions.

AgentDB Vector Search

Name: AgentDB Vector Search
Author: nbossn

bynbossn

0•

データサイエンスとML

Accelerates semantic document retrieval and similarity matching with ultra-fast HNSW indexing and memory-efficient vector storage.

This skill integrates AgentDB's high-performance vector search engine into Claude Code, enabling developers to build sophisticated RAG systems and intelligent knowledge bases with ease. It features sub-millisecond retrieval speeds—often 150x to 12,500x faster than traditional solutions—thanks to advanced HNSW indexing and multi-strategy quantization. Whether you are managing millions of vectors or building a local context-aware agent, this skill provides the CLI tools, API adapters, and MCP integration necessary for high-precision, hybrid semantic search and diverse result sets via Maximal Marginal Relevance (MMR).

主な機能

01Hybrid search capabilities combining vector similarity with metadata filtering

02Multiple quantization modes (Binary, Scalar, Product) for up to 32x memory reduction

030 GitHub stars

04High-speed HNSW indexing with sub-100µs search latency

05Built-in MCP server for direct tool access within Claude Code

06Support for various embedding models including OpenAI, sentence-transformers, and MiniLM

ユースケース

01Creating context-aware memory systems for autonomous AI agents

02Implementing semantic search engines for large-scale technical documentation

03Building high-performance Retrieval-Augmented Generation (RAG) pipelines

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add nbossn/claude-code-base agentdb-vector-search

For use in Claude.ai and ChatGPT

主な機能

01Hybrid search capabilities combining vector similarity with metadata filtering

02Multiple quantization modes (Binary, Scalar, Product) for up to 32x memory reduction

030 GitHub stars

04High-speed HNSW indexing with sub-100µs search latency

05Built-in MCP server for direct tool access within Claude Code

06Support for various embedding models including OpenAI, sentence-transformers, and MiniLM

ユースケース

01Creating context-aware memory systems for autonomous AI agents

02Implementing semantic search engines for large-scale technical documentation

03Building high-performance Retrieval-Augmented Generation (RAG) pipelines

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add nbossn/claude-code-base agentdb-vector-search

For use in Claude.ai and ChatGPT