It’s not really a thing libraries should do tbh, only thing to integrate it would be writing how the effect runtime calls and communicates with the flue sdk, but thats not really a hustle (even though it would be useful)
Next level would be a library fully built with effect, which would be extremely useful. Opencode does this: internally it’s written in effect, and you can use the sdk both through effect or through native typescript (which just calls effect under the hood)
@0xblacklight@FredKSchott@samgoodwin89 I spent al weekend doing an all effect-native agent, and i just kept going back to w|hat @FredKSchott already built, and fitting things together
So I figured a managed runtime is going to do the job. I'm more worried about fitting it well with alchemy
This Week in Effect:
@kitlangton on Cause & Effect, talking about effect systems and OpenCode.
Services & Layers in Production, talk by @leo_trapani
OpenRouter & SailPoint are hiring Effect engineers.
→ https://t.co/hrXfPyx6hm
@mattpocockuk References? My solution to this was to have skill graphs, meaning resources of skills can link to other skills and other resources of skills
At HumanLayer, we’re on a mission to solve the AI slop code problem.
In 2025 we open-sourced our Research, Plan, Implement framework, now deployed inside fortune 500s like Block and Uber - places where shipping slop is just not an option
And that was just the beginning.
Today, we’re opening access to HumanLayer - an Agentic IDE, collaboration platform, and building blocks for your software factory.
HumanLayer enables engineers solving hard problems in complex codebases to:
> move 2-3x faster across the entire SDLC (not just coding)
> maintain rigorous standards for system architecture and program design
Hundreds of engineers at companies of all sizes are already using HumanLayer to ship fast without sacrificing quality.
I'm excited to invite you to try humanlayer today at https://t.co/cQ648EkrnG, and I'm even more excited to see what you build.
@0xblacklight and I are deeply grateful to our team, our customers who give us so much incredible energy and feedback, our investors who have always been in our corner, and our friends and family who have supported us along this crazy journey
if you're a staff or principal engineer trying to make AI coding work at scale for your team, we'd love to hear from you
as @swyx likes to say - let's make this the year of no more slop
DwarfStar now supports SSD streaming in the DGX Spark and Strix Halo, not just in Metal. You can run the Q4 quants at decent speed, and even DeepSeek v4 PRO at low speed, or you can run Q2 Flash if you have less than 128GB.