An agent decides it needs a database to complete its task
It creates one simply by generating a unique ID
The agent can then create a schema or use templates for the tables it needs
Templates also enable agents to properly write data into tables
Remote MCP servers for any combination of databases and templates can be used in AI applications.
All databases are truly serverless so no need to manage compute.
Each database is isolated and can be reused, downloaded, deleted, etc.
import { DatabaseService } from "@agentdb/sdk"
const service = new DatabaseService("https://api.agentdb.dev", "your-api-key")
const db = service.connect("7bd0cf6c-c772-43cf-9047-cd99dc635946", "my_db", "sqlite")
await db.execute({
sql: `CREATE TABLE users (
id INTEGER PRIMARY KEY AUTOINCREMENT,
name TEXT NOT NULL,
email TEXT UNIQUE NOT NULL,
age INTEGER
)`
})Built-in vector search with sqlite-vec extension. Store embeddings, perform semantic search, and build RAG systems.
Choose between SQLite for fast, reliable transactional operations and DuckDB for powerful analytical queries.
Databases are ready instantly. Serverless architecture scales from zero to millions of requests.
$0
$29/month
CUSTOM