# Mastra Projects at AI Tinkerers

> Canonical HTML: https://aitinkerers.org/technologies/mastra
> Markdown URL: https://aitinkerers.org/technologies/mastra.md
> Technology record last updated: 2026-09-18T15:13:40Z
> Generated: 2026-09-22T07:44:41Z

Mastra: The open-source TypeScript framework for building and scaling AI agents, featuring durable workflows, RAG, and a unified router for 40+ LLM providers (OpenAI, Gemini).

Mastra is the leading open-source TypeScript framework for AI agents, launched in 2024 by Gatsby veterans Sam Bhagwat, Shane Thomas, and Abhi Aiyer. This structured platform streamlines AI engineering: it provides autonomous Agents, graph-based Workflows for complex orchestration, and RAG pipelines for grounded responses. The unified model router connects to 40+ LLM providers (e.g., OpenAI, Gemini). Backed by $13M from investors like Y Combinator, Mastra delivers production essentials: built-in Evals, Observability, and a local development playground.

- Official technology site: https://mastra.ai
- Public AI Tinkerers demos and talks: 7
- Result page: 1 of 1

## Recent Public Talks and Demos

### [Building an Enterprise Digital Brain](https://valencia.aitinkerers.org/talks/rsvp_a3Hziwgp_h8)

A Digital Brain is your company's private Wikipedia leveraged with AI. Document every SOP and team member know-how (structured, semi-structured and unstructured) and make it "legible". Then leverage AI to find precise answers quickly, turn them into SKILLS that AI agents can execute. All in one place. In the demo we will look at: - General content storage in a virtual file system - Find precise answers with agentic search - Write natural language skills the agent can execute - Customize chat UX with dynamic tools via skills (work-in-progress)

- Event context: AI Tinkerers Valencia May Meetup — 2026-05-26 — Valencia
- Public talk page: https://valencia.aitinkerers.org/talks/rsvp_a3Hziwgp_h8

### [How to Argue With a Language Model (And Win)](https://belgium.aitinkerers.org/talks/rsvp_RV-s6edPsfU)

You've built an AI agent, it mostly works, and now you're stuck in a loop of tweaking prompts and hoping for the best. Sound familiar? In this talk we'll move past vibes-based development and into structured experimentation. We'll cover how to set up A/B tests for your agents, build and curate datasets from captured interactions or static data, and wire up evals that actually tell you whether your changes made things better or worse.

- Event context: AI Tinkerers Antwerp Meetup - April 1 (no joke) — 2026-04-01 — Belgium
- Public talk page: https://belgium.aitinkerers.org/talks/rsvp_RV-s6edPsfU

### [From Tool Call to React Component: Building Generative UI for Agentic Workflows](https://san-diego.aitinkerers.org/talks/rsvp_d-XLZk6YEb8)

Live demo of a production pattern where AI agents render interactive React components — forms, profile cards, video embeds — directly inline in chat instead of returning plain text. I'll trigger real agent workflows, show the components appearing in the conversation stream, and walk through the completion callback loop where user interaction feeds back into the agent. I'll close with how we codify these multi-step integration patterns as reusable Agent Skills to ship new tools fast.

- Event context: AI Tinkerers San Diego: February Meetup at Google — 2026-02-27 — San Diego
- Public talk page: https://san-diego.aitinkerers.org/talks/rsvp_d-XLZk6YEb8

### [A Browser Agent That Fills Forms For You](https://seattle.aitinkerers.org/talks/rsvp_A6Q-IXcxyD8)

I built a web browsing agent that searches, navigates, and fills out forms on your behalf.

- Event context: The Holiday Science Fair (Hot Cocoa, Cookies, and Demos!) — 2025-12-19 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_A6Q-IXcxyD8

### [Recursive Agentic builder - Build an agent with a prompt.](https://seattle.aitinkerers.org/talks/rsvp_oa_Gc0k0sFs)

Opensource CLI to build a functional agent with a prompt in one shot. Under the hood, there's recursive reinforcement learning system which builds and tests the agent multiple times to improve it.

- Event context: October Meetup - Science Fair at Foundations — 2025-10-23 — Seattle
- Public talk page: https://seattle.aitinkerers.org/talks/rsvp_oa_Gc0k0sFs

### [My best friend is an AI](https://paris.aitinkerers.org/talks/rsvp_uA8S7dyHn_s)

Discussing how Simone, an AI companion built for WhatsApp, has changed my life, and how it's helping thousands of users to feel better. By combining usefullness and personalization, Simone is at the forefront of the AI companion wave.

- Event context: Epic Demo night 0.2.1 - Sep 18th, 2025 — 2025-09-18 — Paris
- Public talk page: https://paris.aitinkerers.org/talks/rsvp_uA8S7dyHn_s

### [A "course" as an MCP Server](https://sf.aitinkerers.org/talks/rsvp_fx3PTLW2j78)

We wanted to build a course for new Mastra devs to get started quickly. However, we knew videos would go out of date and be more difficult to maintain. We decided to launch our "course" as an MCP server. This way your coding agent actually teaches the course content to you and can help you write the code. We think this is a really interactive way to learn. Using an editor with MCP support (such as Cursor, Windsurf, or VSCode), your code agent will call the appropriate MCP tools which will return context for the agent. This context tries to instruct the agent that it should be teaching you the content, not just doing the work for you. We will walk through the code of how it works, what limitations we found, and how we are aiming to further improve this "course."

- Event context: AI Tinkerers - Advanced MCP Showcase — 2025-06-19 — San Francisco
- Public talk page: https://sf.aitinkerers.org/talks/rsvp_fx3PTLW2j78

## Related Technologies

- [TypeScript](https://aitinkerers.org/technologies/typescript) ([Markdown](https://aitinkerers.org/technologies/typescript.md)) — 205 public demos
- [A/B testing](https://aitinkerers.org/technologies/a-b-testing) ([Markdown](https://aitinkerers.org/technologies/a-b-testing.md)) — 3 public demos
- [AI agents](https://aitinkerers.org/technologies/ai-agents) ([Markdown](https://aitinkerers.org/technologies/ai-agents.md)) — 35 public demos
- [AI SDK 6](https://aitinkerers.org/technologies/ai-sdk-6) ([Markdown](https://aitinkerers.org/technologies/ai-sdk-6.md)) — 1 public demo
- [Anthropic](https://aitinkerers.org/technologies/anthropic) ([Markdown](https://aitinkerers.org/technologies/anthropic.md)) — 36 public demos
- [ChatGPT](https://aitinkerers.org/technologies/chatgpt) ([Markdown](https://aitinkerers.org/technologies/chatgpt.md)) — 83 public demos
- [Chrome DevTools Protocol](https://aitinkerers.org/technologies/chrome-devtools-protocol) ([Markdown](https://aitinkerers.org/technologies/chrome-devtools-protocol.md)) — 5 public demos
- [Cursor](https://aitinkerers.org/technologies/cursor) ([Markdown](https://aitinkerers.org/technologies/cursor.md)) — 65 public demos
- [Cursor Agent Skills](https://aitinkerers.org/technologies/cursor-agent-skills) ([Markdown](https://aitinkerers.org/technologies/cursor-agent-skills.md)) — 1 public demo
- [Dataset curation](https://aitinkerers.org/technologies/dataset-curation) ([Markdown](https://aitinkerers.org/technologies/dataset-curation.md)) — 1 public demo
- [Daytona](https://aitinkerers.org/technologies/daytona) ([Markdown](https://aitinkerers.org/technologies/daytona.md)) — 3 public demos
- [Elasticsearch](https://aitinkerers.org/technologies/elasticsearch) ([Markdown](https://aitinkerers.org/technologies/elasticsearch.md)) — 5 public demos
- [Fly](https://aitinkerers.org/technologies/fly) ([Markdown](https://aitinkerers.org/technologies/fly.md)) — 2 public demos
- [Google LLMs](https://aitinkerers.org/technologies/google-llms) ([Markdown](https://aitinkerers.org/technologies/google-llms.md)) — 1 public demo
- [Model evaluation](https://aitinkerers.org/technologies/model-evaluation) ([Markdown](https://aitinkerers.org/technologies/model-evaluation.md)) — 1 public demo
- [Multimodal LLM](https://aitinkerers.org/technologies/multimodal-llm) ([Markdown](https://aitinkerers.org/technologies/multimodal-llm.md)) — 3 public demos
- [Next](https://aitinkerers.org/technologies/next) ([Markdown](https://aitinkerers.org/technologies/next.md)) — 186 public demos
- [Node](https://aitinkerers.org/technologies/node) ([Markdown](https://aitinkerers.org/technologies/node.md)) — 99 public demos