h0rv

This was very interesting and I was fortunate to have my bias validated further for HTMX ;)

I would like to also point out from a small sample of vibe coder friends who are ignorant to tech stacks and just let their agent decide, the default stack is always Next.js, Vercel, and Supabase.

Why are agents when given control to decide, almost always choose Next.js? SEO/AEO?

Aside from a more complex web app for the future benchmark, I have suggestions of what else I'd like to see included:

- Lines of code / surface area of the framework - easier for an agent to find the "right" API when there are fewer - Security surface: number of dependencies per framework - help keep the vibe coders secure - "Number of non-blank source file lines", show both numbers with and without comments included.

Why would you not use an open-source harness in October 2026? I am generally curious - what is the alpha?

Location: Philadelphia, PA

Remote: Yes

Willing to relocate: Yes, for the right opportunity and compensation

Technologies: Go, Python, JavaScript (Node.js), Terraform, C, Java, Rust, Haskell, GNU/Linux, Git, CI/CD, GitHub Actions, AWS, GCP, Azure, IBM Cloud, PostgreSQL, NoSQL, vector databases, Containers, Temporal, Kubernetes

Résumé/CV: https://horv.co/resume/

Email: [email protected]

I've been using d2-mcp in Cursor with Claude Sonnet or Opus (o3 was not great). Cursor provides project structure and details (depending on the level abstraction you want in the diagram) to give really great results.

Before creating d2-mcp, Claude would give okay diagrams, but giving it the ability to "see" what it created, gives it the ability to see its own mistakes and fix them, and optimize for human readability.

  Location: Scranton, PA, USA
  Remote: Yes
  Willing to relocate: Yes to Northeast, USA
  Technologies: Go, Python, Terraform, JavaScript, GNU/Linux, Git, CI/CD, Cloud (IBM Cloud, Azure, AWS), Containers (Docker, Podman), Kubernetes, GenAI/LLMs
  Résumé/CV: https://raw.githubusercontent.com/h0rv/resume/main/resume.pdf
  Email: rhorv+hn@proton[dot]com

Hi, I'm Robby. I am a backend/DevOps Engineer. Passionate about open-source and working on challenging problems. I'm enthusiastic to learn and grow, currently seeking high-growth opportunities where I can contribute in cloud/infra, DevOps, or, ideally, applied AI.

instructor-go is a port of the popular Python package https://github.com/jxnl/instructor.

This implementation uses `jsonschema` and Go struct tags to send data and schema information to the model to return the appropriate response schema.

Currently, OpenAI and Anthropic are supported, and you can see all examples of different capabilities here: https://github.com/instructor-ai/instructor-go/tree/main/exa....

This is in early development and would love some feedback.

Thanks for checking it out!