agentdb

name: agentdb description: "RuVector-powered graph database CLI with Cypher queries, hyperedges, ACID persistence, and 150x faster vector search. Use when managing graph data stores, running Cypher queries, performing vector similarity search, managing database schemas, or building knowledge graphs for AI agents."

AgentDB

AgentDB v2 - RuVector-powered graph database with Cypher query support, hyperedges, ACID persistence, and HNSW vector search. Provides both CLI and programmatic API for graph operations, vector indexing, and knowledge graph management.

Quick Command Reference

Installation

Install: npx agentdb@latest See Installation Guide for hub details.

Core Commands

init

Initialize AgentDB database.

npx agentdb@latest init [--path <dir>] [--force]

start

Start the AgentDB server.

npx agentdb@latest start [--port <n>] [--host <string>]

query

Execute Cypher queries.

npx agentdb@latest query "MATCH (n:User) WHERE n.age > 25 RETURN n"
npx agentdb@latest query --file queries.cypher

search

Vector similarity search.

npx agentdb@latest search --query "authentication patterns" --k 10

import / export

npx agentdb@latest import data.json [--format json|csv|cypher]
npx agentdb@latest export output.json [--format json|csv|cypher]

Programmatic API

import { AgentDB, Graph, HNSWIndex } from 'agentdb';

const db = new AgentDB({ path: './mydb', simd: true });

// Create nodes
await db.createNode('User', { name: 'Alice', age: 30 });
await db.createNode('User', { name: 'Bob', age: 25 });

// Create relationship
await db.createEdge('Alice', 'Bob', 'KNOWS', { since: 2024 });

// Cypher query
const results = await db.query('MATCH (u:User) WHERE u.age > 25 RETURN u');

// Vector search
const similar = await db.vectorSearch(queryVector, { k: 10, ef: 50 });

// Hyperedges
await db.createHyperedge(['Alice', 'Bob', 'Charlie'], 'TEAM', { project: 'alpha' });

RAN DDD Context

Bounded Context: Troubleshooting

References

• Command reference: See references/commands.md
• Full README
• npm