News for hackers. Stuff that matters.

SerafimKorablev

we went through this exact thing. started on vercel ai sdk, migrated to claude code sdk hoping to get the full agent loop out of the box. same conclusion - it's built for single-user cli, not multi-tenant web backends. so we ended up building everything ourselves on top of it. e2b sandboxing per session, env var isolation so credentials can't be exfiltrated from the sandbox, sse streaming, persistent threads, cost tracking, logs and session replay. then the ui side - claude code has plan mode, ask user, permission prompts as native cli tools but none of that translates to a web app, so we had to rebuild all of it as react components. after a few months of this we realized every team shipping agents on claude code or codex is solving the same problems, so we turned our infra into a separate product. docs here if useful - https://21st.dev/agents/docs
Re:Ask HN: Learning resources for building AI agents? on Tuesday April 07, 2026 @06:04PM (#47681933)
We wrote a couple of articles about it, but we were more focused on building on top of CLI-based agents like Claude Code (imagine a lead outreach agent based on Claude Code as an API).

21st.dev/community/blog

Show HN: First Claude Code client for Ollama local models

https://twitter.com/serafimcloud/status/2014266928853110862

Just to clarify the background a bit. This project wasn’t planned as a big standalone release at first. On January 16, Ollama added support for an Anthropic-compatible API, and I was curious how far this could be pushed in practice. I decided to try plugging local Ollama models directly into a Claude Code-style workflow and see if it would actually work end to end.Here is the release note from...

( Read More... | 27 comments | 10 points | on HN )
Thanks for the feedback. We’ve added a short demo video to the repo to clarify the UX and direction. Our focus is earning trust by shipping.
Thank you for the detailed feedback! Really appreciate you taking the time to share these points.

On point 4 (custom answers in Q&A): You're right, this is missing! I'll add the ability to write your own answers today or tomorrow.

On point 1 (scrolling): I pushed a batch of scroll fixes yesterday, but I see it's still not working optimally. We're actively working on improving this - it's definitely on our radar.

On point 2 (split windows): We're planning to add multi-window support soon - so you can have multiple chat windows open side by side, similar to how you'd work with multiple terminal windows, but with a nice UI. Stay tuned!

On point 3 (verbosity control): Great suggestion - sometimes you want to catch assumptions before they cause damage. Adding to our roadmap.

Thanks again, and glad you're finding it useful despite these rough edges!

Show HN: 21st.dev - NPM for Design Engineers Based on Shadcn CLI

https://21st.dev

I originally built this app to organize and reuse interesting React + Tailwind components I came across on Twitter, inspired by the shadcn/ui approach. Later, a friend started contributing their own components, and it got me thinking—this could grow into something bigger, like an NPM for design engineers to share and use components.Would love to hear your thoughts!

( Read More... | 2 comments | on HN )