developers have either adopted Command Code or used the same idea to build repair harnesses for nearly every top coding agent. i take that as more meaningful validation than anything we could say about ourselves. i wrote the idea up openly¹ a few weeks ago, and it has quietly become a de facto way people fix open models. open-model tool-call failures are not deep, they are a small finite set of contract mismatches. so we repair them, with zero token loss. what started as 4 repairs is now the largest repair layer in the space: 36k tool-call fix variants. on the first idea: open models.
we fixed the "open models aren't good enough at tool calling" problem. our research came down to two things, quality and speed, and both trace back to one root cause: broken tool-calls that open models produce, especially when you use a bad harness. we're building for taste and developer experience. so instead of making a soup of thousands of models, we build for the best ones, open or closed. the goal: a coding agent that feels like an iphone, opinionated and with taste, not a random android or a windows phone with no taste. Command Code is built around two ideas:
1. open models should be production-grade for coding.
2. your coding agent should learn your taste. BIG day for us!! Command Code has crossed $1M in annual run rate, 1 trillion tokens of usage, with over 9K customers, just 24 days after beta launch.
We believe this makes it the fastest-growing coding agent harness for open models. 3rd largest by usage. 
given the time period, it was definitely manually routed, but rubber-band topological routing produces similar results and looks cool as well, really want to implement this soon, this is kind of my white whale because it requires time & focus www.ssalewski.de/Router.html.en my new fav supa fast (400tps) and cheap open model.
Step 3.7 Flash just shipped in Command Code $1 Go plan with 10x free usage. 
Step 3.7 Flash is one of the fastest low-cost open models, now live in Command Code. Our $1 Go plan with 10x free usage credits, best way to try it.
• 400 tokens/sec 🍃 • 256K context window • 3 reasoning levels
Sharp instruction-following and strong /design taste. 
Angelo here, totally valid, when running the incident, I didn't have to the account. Now that we are staffed up, we are going to maintain better presence on here. We'll still work to earn your business when you feel the time is right.
What's in your w̶a̶l̶l̶e̶t̶ volumes?
Changelog #0292
• Volume browser in the CLI
• In-browser shell to Priority Boarding
• File browser for buckets
• Fixes and improvements
railway.com/changelog/2026-05-29-cli-volumes 
i watched videodrome a few days ago and the scene that sticks in my head is this brief shot of a circuit board with spectacular routing
check out this blog to understand how data migrations work 👇
pris.ly/data-migrat... In Prisma Next, migrations go beyond schema changes.
They’re versioned TypeScript steps that can reshape data too, so a column rename and its backfill can ship, review, and roll back together. 
How well does Elicit's semantic search work for systematic reviews?
We sampled 888 Cochrane reviews across 12 MeSH areas.
Elicit retrieved 95.0% of included studies on average.
To learn how we evaluated AI search, read: elicit.com/blog/evalua...
Try search on your own questions at Elicit.com. 
Anthropic's Claude Opus 4.8 is now available in Netlify's AI Gateway and Agent Runners.
Use the Anthropic SDK directly in your Functions with zero configuration. Caching, rate limiting, and auth infrastructure are handled automatically.
www.netlify.com/changelog/cl... 
Command Code x Claude Opus 4.8
Opus 4.8 excels at long-horizon agentic coding, large multi-file refactors, ambiguous specs that need pushback, complex multi-step agent runs, and high-autonomy work where reasoning quality matters most.
- Same price as 4.7
- 1M context 
Command Code x Claude Opus 4.8
Opus 4.8 is best for long-horizon agentic coding, large multi-file refactors, ambiguous specs that need pushback, complex multi-step agent runs, and high-autonomy work where reasoning quality matters most.
• Same price as 4.7
• 1M context have the liene pearl N200 on the way, i'll let you know how it goes. bunch of tradeoffs with all the options, lots of proprietary paper + ink combos!
Push & Pull Taste
Share your coding taste with teammates, pull taste from the community. 
📍 Val Town
Other · New York, New York, US
★★★★★
w/ @stevekrouse.com
#BeaconBits read this article to dive deeper 👇
pris.ly/ts-migratio...