Nick Aiyer

[Abhi Aiyer @abhiaiyer]

@mastra engineering is the best team I've ever been a part of. Mission-driven people, ship constantly, and you've seen us moving like we've got something to prove (we do).

We're looking for you, a product engineer, to help us go faster. Apply today 🫵

https://t.co/KkvIl4L5IZ

[Tyler Barnes @tylbar]

🚨We shipped a new context engineering primitive @mastra today, Agent Signals! (alpha)
🔓Unlocks: multiplayer steering, dynamic cacheable system prompts, agent notifications (gh/email/etc), and automatic behavior guidance 🧵

[Alex Booker @bookercodes]

Stoked to announce Mastra Observability - hosted observability for Mastra agents 🔥

Export high-volume traces and logs

Monitor cost and performance, search and filter every run

Then use Studio to turn production behavior into evals, datasets, and experiments

[Sam Bhagwat @calcsam]

We’re excited to announce today that @mastra has raised a $22M Series A led by Spark Capital.

This brings our total capital raised to $35M:

[Alex Booker @bookercodes]

Today we're launching @mastra remote sandboxes

Give your agent a secure, isolated environment to run untrusted user code... like a vibe coding agent...

[Mastra @mastra]

https://t.co/wCCwUhoWa3

[Sam Bhagwat @calcsam]

ts ai conf launch #4

you may have read my book: Principles of Building AI Agents

well, we wrote a sequel: Patterns for Building AI Agents

about bridging the gap where AI teams stumble

between prototype and production

if you like and share this post we will send you a copy

[Sam Bhagwat @calcsam]

ts ai conf launch #3

we believe developers deserve beautiful tools.

today we are excited to announce a new logo and brand for Mastra

we wanted something that would represent the dynamism and fluidity of agents

[Sam Bhagwat @calcsam]

ts ai conf launch #2

we keep getting asked about patterns for using @aisdk ui, @assistantui, and @CopilotKit with mastra

so we built UI Dojo, a repo + frontend with mastra agents implemented in each of these

we are committed to first-class support for all of them

[Mastra @mastra]

our old livestream failed

so heres the new one: https://t.co/4LboHxF3LA

[Nick Aiyer @nik_aiyer]

https://t.co/t9YvYtxnQY

[Nick Aiyer @nik_aiyer]

deploy your evals to mastra cloud

you can just deploy things

[Nick Aiyer @nik_aiyer]

More details here: https://t.co/agrFPY9j5X

[Nick Aiyer @nik_aiyer]

📝 Memory: Organize conversation threads with resource IDs

🔄 Workflow: Pause and resume complex states

📊 Evaluation: Track performance metrics

🔍 Observability: Debug with OpenTelemetry traces

[Nick Aiyer @nik_aiyer]

Or use other providers such as Upstash or Clickhouse.

Your interface stays the same.

[Nick Aiyer @nik_aiyer]

Mastra Storage solves this. It’s easy to use when starting and also when scaling. Here’s what it manages: 👇

[Nick Aiyer @nik_aiyer]

Introducing Mastra Storage 🚀

Building AI apps? Data management gets complex fast.

You need to handle:

• Conversation histories across multiple turns

• Workflow states

• Evaluation metrics

• Monitoring data