Mastra
@mastra_ai
Followers
7K
Following
2K
Media
32
Statuses
880
the typescript framework for building agents by @calcsam @smthomas3 @abhiaiyer @tonykovanen @wardpeet @tylbar and many others
Joined November 2024
the wait is over tickets just dropped for the first conference for typescript ai: https://t.co/zhd3xfAbwp featuring @swyx, @grinich, @alanaagoyal, @MarcKlingen, @pk_iv, @zeeg & others nov 6th | SF and virtual | 300 spots | builders only
6
13
58
Seen a few people ask how to use @Mastra_ai with AI SDK UI I made an example with React and Vite to show you how 👇🏻
2
9
31
early bird tickets are live ... only for a few more mins down to the last 5 https://t.co/zhd3xfAbwp
0
3
11
Just released new @mastra_ai template: PDF ➜ crisp natural audio Shows how to - Naturalize text - Generate audio stream w/ OpenAI TTS - Optimize token usage for hefty PDFs Link below
3
4
12
cathedrals everywhere
2
0
15
👀
One more thing. Agent 3 can now generate your own agents. Agents that can work with you in Slack or Telegram. Or run based on schedule or trigger based on webhook events. Enrich it with your own data sources, and build automations with apps like Notion, Linear, Dropbox, etc.
1
2
9
powered by mastra
One more thing. Agent 3 can now generate your own agents. Agents that can work with you in Slack or Telegram. Or run based on schedule or trigger based on webhook events. Enrich it with your own data sources, and build automations with apps like Notion, Linear, Dropbox, etc.
7
7
74
but wait... how does Agent 3 build those other agents? 👀
AI agents can prototype apps… But shipping real software takes hours of testing, debugging, and refactoring. Agent 3 is 10× more autonomous — it keeps going where others get stuck. The “Full Self-Driving” moment of software.
2
6
30
shoutout to our community for helping us grow
shoutout to the @mastra_ai team for fixing stuff so fast !
0
0
6
on how to best implement human-in-the-loop https://t.co/ApdJYk7l7W
Random YouTube comment: How do I implement human-in-the-loop with @Mastra_ai ? Me: Here's the best introduction video to `suspend` and `resume` I know how to make
0
0
0
on GPT-OSS vs other models https://t.co/VwL0cvIsiw
Honestly, when OpenAI’s new models were announced, I didn’t fully get the hype. I wondered: - How good is GPT-OSS compared to proprietary models? - What does this shift mean for the industry? - Can I actually build a local agent with it? I made this video to explore those
0
0
1
on why stuffing your context window isnt enough https://t.co/hppmuNczdM
with huge context windows, you might think you can just stuff everything in you can't in practice, large language models still hit real limits. that's where context engineering comes in
2
0
1
on templates ( https://t.co/AMMIuTaZMS)
https://t.co/nHQD7cltDp
hey friends, this month I'm working with @mastra_ai to help them launch templates! there are many new templates to talk about, but my favourite is this text-sql one we built never write a sql query again! just query the db in natural language 🚀
1
0
1