Research

In-depth technical articles on AI agents, RAG, memory, and the systems behind them.

Decision Models Get Context Rot Too

We padded 400 questions with up to 26k tokens and compared Jev, Clef and GPT-6 Luna Decisions with reasoning and non-reasoning LLMs.

Oct 16, 2026

10 min read

Observational Memory: 95% on LongMemEval

How we built a human-inspired memory system that achieves the highest score ever recorded on LongMemEval

Feb 9, 2026

15 min read

Yes, you can use RAG for agent memory

How we spent $8k to prove RAG isn't dead

Jul 17, 2025

12 min read

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