Igor Costa

Building @Autohandai , former @Microsoft, @GitHub, @AWS.

[Igor Costa @igorcosta]

Welcome little fella. It’s now available on @autohandai Code

[Google Gemma @googlegemma]

Meet Gemma 4 12B!

A unified, encoder-free multimodal model designed to bring high-performance intelligence directly to your laptop, and released under an Apache 2.0 license.

Bridging the gap between edge efficiency and advanced reasoning. Here is what’s new with Gemma 4 12B: 👇

[Igor Costa @igorcosta]

@cognition Add an agent that you trust and evolve with you: autohand - - mode acp paired With Devin Desktop…

[Igor Costa @igorcosta]

@mattbergland Looks like it doesn’t have @autohandai code cli, in the site. Hint: autohand - - mode acp

[Igor Costa @igorcosta]

Thank you for having me @aiDotEngineer Melbourne, @swyx maybe next time we have a chance to meet.

[Igor Costa @igorcosta]

@amasad @Microsoft Nice

[Igor Costa @igorcosta]

@Prince_Canuma Congratulations Prince, I’m happy to invest!

[Igor Costa @igorcosta]

I must admit, I’m pretty happy to be surrounded by like-minded people.

[Autohand AI @autohandai]

We’re here Melbourne for @aiDotEngineer this week.

@igorcosta is presenting a keynote on the next generation of memory for coding agents.

Why do agents forget?

What does persistent memory actually look like?

Visit us at Booth 12 and chat with the @autohandai team.

[Igor Costa @igorcosta]

@badlogicgames Welcome to this bandwidth!

[Igor Costa @igorcosta]

@QingQ77 Amazing work!

[Igor Costa @igorcosta]

AI Software factory age begins

[Autohand AI @autohandai]

Today we are announcing Autohand Code Enterprise.

We started with a CLI because real software work still happens in the terminal, usually one bad deploy away from character development.

Now we are bringing that same foundation to companies.

https://t.co/hfII2iiJtw

[Igor Costa @igorcosta]

@billxbf That’s cool! We researched this last year https://t.co/zEhgLeeeBZ Gotta see your take on this, very curious

[Igor Costa @igorcosta]

@mike_matas Neat Mike

[Igor Costa @igorcosta]

@svpino Why don’t you use https://t.co/9FwPprCVCd ?!

[Igor Costa @igorcosta]

@AmpCode Nice feels a lot like what I wrote a year ago https://t.co/CX4ZKNVwQO and is the foundation of manifesto https://t.co/xfSuZJBJwX

[Igor Costa @igorcosta]

@charles_irl Impressive!

[Igor Costa @igorcosta]

@zenorocha @dsog @braintrust 20 cases? You’re not doing evals you’re doing prompt optimizations. GEPA is your best friend for that.

[Qwen @Alibaba_Qwen]

Performance：Qwen3.7-Max performs strongly across benchmarks in coding agents , and improves massively in general-purpose agents. Qwen3.7-Max also demonstrates exceptional strength on the hardest reasoning benchmarks, and stands out in general capabilities and multilingualism.

[Igor Costa @igorcosta]

@swyx I'm going to use this in my talk at @aiDotEngineer Melbourne, hoping you don't mind! and looking forward to meet you.

[Igor Costa @igorcosta]

we just crossed 150k DaU. @autohandai Code comes with all batteries included and open and supports 25 LLMs for coding, BYOK for now.

I truly appreciate this platform users. Thank you!

[Igor Costa @igorcosta]

@nbaschez @bentossell @narphorium