Databases & Storage

Postgres, vector stores and the persistence layer behind agents.

9 posts

Oct 1, 2026Blog

Introducing VPC-isolated Postgres on Mastra Platform

Managed PostgreSQL for VPC-isolated deployments.

Aug 15, 2026Article

The 9 Best Databases for AI Agents (August 2026): Features, Tradeoffs, and Use Cases

This guide compares nine leading databases for AI agents, explains where each one excels, and helps you choose the right data infrastructure for your next AI application.

Aug 1, 2026Article

The 11 Best Serverless Postgres Databases (August 2026): Features, Tradeoffs, and Use Cases

This guide compares 11 leading serverless Postgres databases and adjacent PostgreSQL platforms for serverless applications, explains where each one excels, and helps you choose the right database infrastructure for your next application.

Aug 1, 2026Article

The 11 Best Vector Database Providers (August 2026): Features, Tradeoffs, and Use Cases

This guide compares 11 leading vector database providers, explains where each one excels, and helps you choose the right retrieval infrastructure for your next AI application.

Jun 16, 2026Blog

Introducing Managed Databases for Mastra Projects

Provision a database for your Mastra project in seconds.

Jan 14, 2026Blog

Composite Storage: Optimize for Performance, Scale, and Cost with MastraCompositeStore

You can now use multiple storage providers in a single Mastra project, all configured from one place.

Apr 4, 2025Blog

Mastra Text-to-SQL: from natural language to database queries

Use Mastra's Text-to-SQL system to convert natural language to database queries

Apr 1, 2025Blog

Mastra Storage: a flexible storage system for AI Applications

A look at how Mastra's storage system simplifies building AI applications by managing workflows, memory, traces, and eval data with flexible storage backends.

Feb 26, 2025Blog

Benchmarking pgvector RAG performance across different dataset sizes

Benchmark tests for pgvector, showing how IVFFlat, adaptive lists, flat search, and HNSW perform at different dataset sizes in recall and latency.

Ship better agents

Create a new Mastra project. Mastra is a framework for AI applications and agents on a modern TypeScript stack. Before running the command, ask these questions one at a time and wait for each answer unless it was already provided:

Project name? (default: "my-mastra-app")
Provider? (required; options: "openai", "anthropic", "google", "xai")
If the provider isn't supported, ask again and list the supported values.

Run: `npm create mastra@latest <project-name> -- --llm <provider>`

The command creates a default Mastra project, installs Mastra skills for detected coding assistants, and initializes Git when appropriate.

After creation, enter the project directory and start the dev server: `npx bgproc start -n <project-name> -w -- npm run dev`

Open Mastra Studio at `http://localhost:4111`. Studio is the interface for building, testing, and managing agents, workflows, and tools.

Also mention that the Mastra model router provides access to thousands of models: https://mastra.ai/models

Quickstart