⚡ Building for the web is my passion. Web UIs at scale, cost-efficient cloud infra. Polishing the craft with AI agents. Husband & dad of 3
Atlanta
Joined March 2009
- Tweets11.9K
- Following1.4K
- Followers935
- Likes9.3K
Daniel Endara retweeted
Cloudflare CLI is now in beta. It unifies Workers, DNS, and security management into a single tool that works great with coding agents.
developers.cloudflare.com/ch…
Daniel Endara retweeted
We’re now live in Ecuador with @Starlink Mobile! The new service with @CNT_EC will connect people in cellular dead zones across the country’s diverse terrains including the Amazon rainforest and Galápagos Islands.
El día cero llegó para nosotros, la alianza CNT x @Starlink es oficial desde hoy.
Te mantendremos conectado siempre gracias a Starlink Mobile, la tecnología direct-to-device más grande del mundo.
Daniel Endara retweeted
Because this “Meta uses OpenClaw” story is going around. They built their own agent, being inspired. Nat and his team did a great job. Kudos!
we built muse from scratch, but it is definitely heavily inspired as a product by openclaw. After I used openclaw in january I bought hundreds of mac minis for the MSL team and lots of us fell in love with using openclaw (and other personal agents). @steipete is a genius and his harness was pioneering from the jump. I think a lot of people were inspired by it. our goal with muse was to build something like openclaw that we could make safe and secure and easy to use and scale to billions of people.
Daniel Endara retweeted
Burnbar for Omarchy now budgets your remaining subscription tokens so you can "make it" to the reset.
I wasnt budgeting my usage well so I updated Burnbar keep tabs for me...
github.com/nixfred/burnbar
Daniel Endara retweeted
We just rolled out CursorBench 4.0!
It includes new tasks for how well models follow instructions, work on challenging projects over time, and is more difficult than before (so all models score lower).
Daniel Endara retweeted
I’ve been full-time on @OmarchyLinux for 3 days now.
It’s a huge unlock to have an OS that agents can fully customize/fix/improve.
A short example from today:
I was scheduled to record a big podcast and I wanted my audio and video to be perfectly tuned.
I simply asked Fable 5.1 to do it.
It wrote a script to test my audio.
Then it took the results and adjusted all the settings.
It then found a TUI app for Shure to show me what changes it had made.
It then added the TUI app as an Omarchy app so I can pull it up anytime I want.
Daniel Endara retweeted
Hey @dhh the Atlanta #Omarchy Meetup is live!
Founding members:
@Justin_Starner
@navindra404
@augman - Organizer
@jttraino
@NixFred
Daniel Endara retweeted
Running Gemma 4 26B A4B on a Mac just got 2x faster!
The developer community has been grinding on the mlx.fast leaderboard, pushing Apple Silicon to its limits.
Daniel Endara retweeted
OBSIDIAN JUST GOT A CLI.
NOW CLAUDE CODE AND AI AGENTS CAN CREATE, SEARCH AND UPDATE YOUR VAULT DIRECTLY FROM THE TERMINAL.
Daniel Endara retweeted
At 250 billion DNS cache entries, one wasted byte costs 250 GB of RAM.
Five Rust optimizations later: 100 TB freed, inserts 43% faster, lookups 19% faster.
We didn't trade speed for space. cfl.re/4gyL9Jj
Daniel Endara retweeted
exo featured on Apple's new M5 Ultra Mac Studio and M6 / M5 Pro Mac Mini pages.
Over the past year, we have worked closely with Apple on low-latency RDMA networking over Thunderbolt 5, enabling clusters of Macs to run massive models like Kimi K3 and GLM-5.3 at API speeds.
With RDMA, aggregate memory bandwidth across Macs scales ~linearly.
A cluster of 4 x M5 Ultra Mac Studios scale to an aggregate memory bandwidth of ~4.8TB/s. Previously, these were speeds only achievable with data center GPUs.
Our vision is a data center on every desk. Apple Silicon's superior memory unit economics, power efficiency, and out of the box experience for Local AI make that possible.
Thank you to @angeloskath, @awnihannun, @twid and countless others at Apple who tirelessly to bring this technology to the world.
Daniel Endara retweeted
You don't always need a frontier model.
A recent benchmark found that Gemma 4 31B matches Sonnet 5 on answer quality at ~40x lower cost.
With high cost-efficiency and low latency, Gemma unlocks high-volume use cases that are uneconomical with larger models.
Daniel Endara retweeted
Congratulations to the whole @GoogleDeepMind Gemma team!
Gemma is one of the most popular open models.
It's been an amazing journey being a close partner! Can't wait to see what's to come! 🎉
Daniel Endara retweeted
Ready to debug Angular apps with AI? 🤖
Angular v22 brings experimental integration with Chrome DevTools for Agents. Tools like angular:signal_graph and angular:di_graph let agents inspect your signals & DI logic.
Try it in DevTools MCP today. See PRs #67985 github.com/angular/angular/p… & #68030 github.com/angular/angular/p…🔍
