AgentDB Vector Search
Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying
Install / Use
npx skills add Microck/ordinary-claude-skills --skill agentdb-vector-searchInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
Data & AnalyticsSupported Platforms
Our assessment of AgentDB Vector Search
AgentDB Vector Search scores 90/100 on our quality scale, 262nd of 598 Data & Analytics skills we index (top 44%).
Its SKILL.md is 8.7 KB long, well organised into 81 sections with 20 code examples: a thorough specification that gives an agent plenty to work with.
It has 399 GitHub stars, a meaningful sign that others use it.
Maintenance, license and trust
- The repository was last updated about 3 months ago, so AgentDB Vector Search is actively maintained.
- Our last check on 2026-11-20 found the source still online.
- No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
- Its trust signals score 88/100, with 1 caution from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
No issues foundOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.
AI review by kimi-k2.7-code on 2026-10-07. Automated pattern scan on 2026-10-07. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
AgentDB Vector Search compared with similar skills
All 4 of these similar skills score higher than AgentDB Vector Search; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| AgentDB Vector Search (this skill)by Microck | 90 | 399 | 3mo ago | SKILL.md |
| algorithmic-artby anthropics | 100 | 177.9k | 2mo ago | SKILL.md |
| pptxby anthropics | 100 | 177.9k | 2mo ago | SKILL.md |
| prospectingby coreyhaines31 | 100 | 60.1k | 11d ago | SKILL.md |
| ad-creativeby coreyhaines31 | 100 | 60.1k | 11d ago | SKILL.md |
Frequently asked questions
- How do I install AgentDB Vector Search?
- Run
npx skills add Microck/ordinary-claude-skills --skill "AgentDB Vector Search". The install tabs above show the steps for each supported agent. - Which AI agents does AgentDB Vector Search work with?
- It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is AgentDB Vector Search safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It declares no license and scores 88/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is AgentDB Vector Search still maintained?
- The repository was last updated about 3 months ago, so AgentDB Vector Search is actively maintained.
Skill content
View source on GitHubname: "AgentDB Vector Search" description: "Implement semantic vector search with AgentDB for intelligent document retrieval, similarity matching, and context-aware querying. Use when building RAG systems, semantic search engines, or intelligent knowledge bases."
AgentDB Vector Search
What This Skill Does
Implements vector-based semantic search using AgentDB's high-performance vector database with 150x-12,500x faster operations than traditional solutions. Features HNSW indexing, quantization, and sub-millisecond search (<100µs).
Prerequisites
- Node.js 18+
- AgentDB v1.0.7+ (via agentic-flow or standalone)
- OpenAI API key (for embeddings) or custom embedding model
Quick Start with CLI
Initialize Vector Database
# Initialize with default dimensions (1536 for OpenAI ada-002)
npx agentdb@latest init ./vectors.db
# Custom dimensions for different embedding models
npx agentdb@latest init ./vectors.db --dimension 768 # sentence-transformers
npx agentdb@latest init ./vectors.db --dimension 384 # all-MiniLM-L6-v2
# Use preset configurations
npx agentdb@latest init ./vectors.db --preset small # <10K vectors
npx agentdb@latest init ./vectors.db --preset medium # 10K-100K vectors
npx agentdb@latest init ./vectors.db --preset large # >100K vectors
# In-memory database for testing
npx agentdb@latest init ./vectors.db --in-memory
Query Vector Database
# Basic similarity search
npx agentdb@latest query ./vectors.db "[0.1,0.2,0.3,...]"
# Top-k results
npx agentdb@latest query ./vectors.db "[0.1,0.2,0.3]" -k 10
# With similarity threshold (cosine similarity)
npx agentdb@latest query ./vectors.db "0.1 0.2 0.3" -t 0.75 -m cosine
# Different distance metrics
npx agentdb@latest query ./vectors.db "[...]" -m euclidean # L2 distance
npx agentdb@latest query ./vectors.db "[...]" -m dot # Dot product
# JSON output for automation
npx agentdb@latest query ./vectors.db "[...]" -f json -k 5
# Verbose output with distances
npx agentdb@latest query ./vectors.db "[...]" -v
Import/Export Vectors
# Export vectors to JSON
npx agentdb@latest export ./vectors.db ./backup.json
# Import vectors from JSON
npx agentdb@latest import ./backup.json
# Get database statistics
npx agentdb@latest stats ./vectors.db
Quick Start with API
import { createAgentDBAdapter, computeEmbedding } from 'agentic-flow/reasoningbank';
// Initialize with vector search optimizations
const adapter = await createAgentDBAdapter({
dbPath: '.agentdb/vectors.db',
enableLearning: false, // Vector search only
enableReasoning: true, // Enable semantic matching
quantizationType: 'binary', // 32x memory reduction
cacheSize: 1000, // Fast retrieval
});
// Store document with embedding
const text = "The quantum computer achieved 100 qubits";
const embedding = await computeEmbedding(text);
await adapter.insertPattern({
id: '',
type: 'document',
domain: 'technology',
pattern_data: JSON.stringify({
embedding,
text,
metadata: { category: "quantum", date: "2025-01-15" }
}),
confidence: 1.0,
usage_count: 0,
success_count: 0,
created_at: Date.now(),
last_used: Date.now(),
});
// Semantic search with MMR (Maximal Marginal Relevance)
const queryEmbedding = await computeEmbedding("quantum computing advances");
const results = await adapter.retrieveWithReasoning(queryEmbedding, {
domain: 'technology',
k: 10,
useMMR: true, // Diverse results
synthesizeContext: true, // Rich context
});
Core Features
1. Vector Storage
// Store with automatic embedding
await db.storeWithEmbedding({
content: "Your document text",
metadata: { source: "docs", page: 42 }
});
2. Similarity Search
// Find similar documents
const similar = await db.findSimilar("quantum computing", {
limit: 5,
minScore: 0.75
});
3. Hybrid Search (Vector + Metadata)
// Combine vector similarity with metadata filtering
const results = await db.hybridSearch({
query: "machine learning models",
filters: {
category: "research",
date: { $gte: "2024-01-01" }
},
limit: 20
});
Advanced Usage
RAG (Retrieval Augmented Generation)
// Build RAG pipeline
async function ragQuery(question: string) {
// 1. Get relevant context
const context = await db.searchSimilar(
await embed(question),
{ limit: 5, threshold: 0.7 }
);
// 2. Generate answer with context
const prompt = `Context: ${context.map(c => c.text).join('\n')}
Question: ${question}`;
return await llm.generate(prompt);
}
Batch Operations
// Efficient batch storage
await db.batchStore(documents.map(doc => ({
text: doc.content,
embedding: doc.vector,
metadata: doc.meta
})));
MCP Server Integration
# Start AgentDB MCP server for Claude Code
npx agentdb@latest mcp
# Add to Claude Code (one-time setup)
claude mcp add agentdb npx agentdb@latest mcp
# Now use MCP tools in Claude Code:
# - agentdb_query: Semantic vector search
# - agentdb_store: Store documents with embeddings
# - agentdb_stats: Database statistics
Performance Benchmarks
# Run comprehensive benchmarks
npx agentdb@latest benchmark
# Results:
# ✅ Pattern Search: 150x faster (100µs vs 15ms)
# ✅ Batch Insert: 500x faster (2ms vs 1s for 100 vectors)
# ✅ Large-scale Query: 12,500x faster (8ms vs 100s at 1M vectors)
# ✅ Memory Efficiency: 4-32x reduction with quantization
Quantization Options
AgentDB provides multiple quantization strategies for memory efficiency:
Binary Quantization (32x reduction)
const adapter = await createAgentDBAdapter({
quantizationType: 'binary', // 768-dim → 96 bytes
});
Scalar Quantization (4x reduction)
const adapter = await createAgentDBAdapter({
quantizationType: 'scalar', // 768-dim → 768 bytes
});
Product Quantization (8-16x reduction)
const adapter = await createAgentDBAdapter({
quantizationType: 'product', // 768-dim → 48-96 bytes
});
Distance Metrics
# Cosine similarity (default, best for most use cases)
npx agentdb@latest query ./db.sqlite "[...]" -m cosine
# Euclidean distance (L2 norm)
npx agentdb@latest query ./db.sqlite "[...]" -m euclidean
# Dot product (for normalized vectors)
npx agentdb@latest query ./db.sqlite "[...]" -m dot
Advanced Features
HNSW Indexing
- O(log n) search complexity
- Sub-millisecond retrieval (<100µs)
- Automatic index building
Caching
- 1000 pattern in-memory cache
- <1ms pattern retrieval
- Automatic cache invalidation
MMR (Maximal Marginal Relevance)
- Diverse result sets
- Avoid redundancy
- Balance relevance and diversity
Performance Tips
- Enable HNSW indexing: Automatic with AgentDB, 10-100x faster
- Use quantization: Binary (32x), Scalar (4x), Product (8-16x) memory reduction
- Batch operations: 500x faster for bulk inserts
- Match dimensions: 1536 (OpenAI), 768 (sentence-transformers), 384 (MiniLM)
- Similarity threshold: Start at 0.7 for quality, adjust based on use case
- Enable caching: 1000 pattern cache for frequent queries
Troubleshooting
Issue: Slow search performance
# Check if HNSW indexing is enabled (automatic)
npx agentdb@latest stats ./vectors.db
# Expected: <100µs search time
Issue: High memory usage
# Enable binary quantization (32x reduction)
# Use in adapter: quantizationType: 'binary'
Issue: Poor relevance
# Adjust similarity threshold
npx agentdb@latest query ./db.sqlite "[...]" -t 0.8 # Higher threshold
# Or use MMR for diverse results
# Use in adapter: useMMR: true
Issue: Wrong dimensions
# Check embedding model dimensions:
# - OpenAI ada-002: 1536
# - sentence-transformers: 768
# - all-MiniLM-L6-v2: 384
npx agentdb@latest init ./db.sqlite --dimension 768
Database Statistics
# Get comprehensive stats
npx agentdb@latest stats ./vectors.db
# Shows:
# - Total patterns/vectors
# - Database size
# - Average confidence
# - Domains distribution
# - Index status
Performance Characteristics
- Vector Search: <100µs (HNSW indexing)
- Pattern Retrieval: <1ms (with cache)
- Batch Insert: 2ms for 100 vectors
- Memory Efficiency: 4-32x reduction with quantization
- Scalability: Handles 1M+ vectors efficiently
- Latency: Sub-millisecond for most operations
Learn More
- GitHub: https://github.com/ruvnet/agentic-flow/tree/main/packages/agentdb
- Documentation: node_modules/agentic-flow/docs/AGENTDB_INTEGRATION.md
- MCP Integration:
npx agentdb@latest mcpfor Claude Code - Website: https://agentdb.ruv.io
- CLI Help:
npx agentdb@latest --help - Command Help:
npx agentdb@latest help <command>
Related Skills
algorithmic-art
177.9kCreating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems.
pptx
177.9kUse this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx or .potx file (even if the extracted content will be used elsewhere, like in an em…
prospecting
60.1kWhen the user wants to find and qualify prospects for outbound, or asks who to target first, which signal to prioritize, or where to spot buyers with the problem: buying signals, enrichment, verification, account research.
ad-creative
60.1kWhen the user wants to write or judge ad creative, or asks which ad, hook, or angle to run or kill: headlines, primary text, and variations for Google, Meta, LinkedIn, and TikTok, fresh angles when creative fatigues. Test hypotheses name the metric, comparison, and expected direction.
Languages
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
