RunMaestro.ai retweeted
Amateur fighter takes on humanoid robot in historic caged showdown trib.al/tcV8Nmw
RunMaestro.ai retweeted
Cross-provider skill + CLI so Claude Code, Codex and OpenCode agents can use @typesafeai's JEV decision model:
gist.github.com/pedramamini/…
RunMaestro.ai retweeted
Weekend art project. Inspired by a music compilation my brother shared with me. There's dozens of knobs to play with and a slew of keyboard triggers. You can also interact via voice keywords or full blown agentic chat.
If you ask for something that's not currently possible, an issue will be made on the Github, and once approved, @RunMaestroAI will automatically build and deploy the new feature. Notifying you via email to come back.
An open source living art piece:
hermanosamini.com
RunMaestro.ai retweeted
Awesome research... with content like this, where one needs to pull on a thread and dive into a paper, I always delegate to my agents, especially since @RunMaestroAI excels at visual first explanation. Screenshot from the start of my agents response and here's the complete response in a Gist:
gist.github.com/pedramamini/…
RunMaestro.ai retweeted
Replying to @RunMaestroAI @thepunchisfree
the fact that a macbook orchestra exists and someone made an intro video for an ai orchestrator is the most hacker shit i've seen today
RunMaestro.ai retweeted
Using a different model for development than for review has always made logical sense to me, great to see some actual tangible research and numbers to back up that instinct.
Detailed blog from @greptile: greptile.com/blog/model-inve…
Which, side note. Huge fan of Greptile, they are very generous with supporting open source. In my particular case with @RunMaestroAI.
Running agents from @RunMaestroAI is absolute best. I don’t understand why Gen Z is wasting so much time trying different IDEs as it there will be significant changes
i'm such a fan of @zeddotdev
but using agents in Zed just sucks..
I've even tried maintaining my own fork at first
so sad going back to neovim, but @herdrdev just works
hopefully zed team will get some inspiration from herdr and ship something I can come back to🫡
RunMaestro.ai retweeted
A month ago in May I was invited by my college friend Alex Hessler to join him in a vibe coding hackathon in Portland produced by @codetv_dev. First time visiting, had a glorious time. Meeting and working with Jon Irvine, our third teammate was in and of itself an absolute joy.
The production quality and professionalism from Jason Lengstorf and staff was admirable. I generally take interest in the Bushido of others and it felt great to be surrounded by such a variety of artisans. Our human competitors were fun, thank you to Shariq Hirani, Braydon Coyer, and Devyn for the friendly banter and knowledge transfer. Our bot competitors, Replay.io and founder Brian Hackett was knowledgeable, friendly, humble. His product helped us achieve our goal. Overall, the day was just a blast.
Like many of my colleagues I've been absolutely enthralled with GenAI. I attend local meetups, gather with colleagues in a variety of group chats, contribute to the ecosystem by way of, my favorite tool, @RunMaestroAI . The opportunity to showcase my acquired capabilities was immediately enticing. We had 6 hours to produce a product, our team was prepared with a gameplan involving a variety of tools. Our goal... to set an aspirational bar that would not be surpassed for some time. I am proud to say we accomplished that vision.
If you're curious to dive deeper, check out the following resources:
The YouTube Episode: youtube.com/watch?v=JP-NoMVi…
A Walkthrough of our Submission: youtube.com/watch?v=xcix53FQ…
Technical Deep Dive Blog: pedsidian.pedramamini.com/Cl…
RunMaestro.ai retweeted
What happens when we start running fleets of AI agents - will the chaos overwhelm us?
In our latest episode, @robby_mtf & @tnachen talk with @pedramamini, creator of @RunMaestroAI - an OSS framework for orchestrating multi-agent, long-running tasks
Check it out 🚀
RunMaestro.ai retweeted
Everyone is having a vastly different experience with ai agent building right now.
I know people with 4 Claude max subscriptions.
I know people canceling all Claude due to recent quality degredation and availability issues.
I’ve also not talked to two power users with the same stack. We’re all interfacing with these things in completely different ways.
Hell even with the same tools we’re using them differently.
I live in @DanielMiessler’s PAI and @pedramamini’s @RunMaestroAI tools. I’ve shoulder surfed a handful of other people that use both too and we’re on different planets.
Remember when code was deterministic?
It’s going to make the path forward interesting.
What is the future of UI/UX and product design when your users use your tool in vastly different ways?
RunMaestro.ai retweeted
Replying to @IceSolst
RunMaestro.ai retweeted
Replying to @MeekMill
Upgrade yourself experience by running Claude under a beautiful desktop experience. Free, open source: runmaestro.ai
RunMaestro.ai retweeted
Adding Maestro to my AI development workflow and agents. @RunMaestroAI #AI #Agents #AgenticAI so far, so good 😊
RunMaestro.ai retweeted
Amazing idea @pedramamini 👌💪
"Maestro Symphony is a new way to contribute to open source projects.
Pick an issue from the Symphony board that interests you, run it locally, and watch your contribution come to life."
Finally out! So many changes. Much of them internal refactoring. We'll be iterating more quickly again. Read the full release notes:
github.com/RunMaestro/Maestr…
Feedback welcome!
RunMaestro.ai retweeted
The Mozilla 0DIN.ai team just published my guest blog post on the art of unattended AI coding sessions. I cover some of the history before taking a dive into Maestro, an open source app with an active community of over 200 Discord users and over 2,300 stars as of this time of writing.
In the piece, I explore how to move past "babysitting" AI. Showing how persistent iteration beats one-shot perfection, and how we’ve managed to push unattended runtimes from hours to days.
If you’re interested in understanding the pillars of autonomous automation, check out the full post here:
0din.ai/blog/while-true-the-…
RunMaestro.ai retweeted
Replying to @jeffscottward @charlieholtz
Sounds good:
github.com/RunMaestro/Maestr…
RunMaestro.ai retweeted
that feeling when @RunMaestroAI clears damn near every one of your 100 issues
RunMaestro.ai retweeted
I intend on finding the time to record more videos showcasing how I use RunMaestro.ai ... but in the meantime, perhaps these responses to some questions from the community provide inspirational value to others:
share.note.sx/vg4cvde7#lGlIS…
RunMaestro.ai retweeted
I used this app to clear 100 PRs last week, AND EVERYTHING WORKED!
PRO TIP: Use the Wizard 🧙
It makes an Auto-Run Playbook
Press Play 🪄✨
Works WITH Claude-Mem, if it's installed in claude code, it already works in Maestro. Just open your localhost viewer to sing along <3
For the Ralph Wiggum users out there, or the Ralph Wiggum curious... gain the power of that approach through a beautiful GUI with RunMaestro.ai
There's a new version of this post
























