@Jack_Timonen · X

@vitverb · X

hi :) One tap back to the work you meant to finish. No tasks to manage. Nothing to set up. Local-first

@JohnTremendol · X

does this look vibe coded?

FabianBeiner · HN

CMEM – Persistent Memory for AI Coding Agents

@0shuvo0 · X

vpetroff · HN

CobaltCode – Dedicated persistent computer for Codex

@manoj_surya_ · X

I just launched 🚀 A Proof of Ship, every day — straight from your GitHub. You already do the hard part: you commit. git-to-x turns that into a designed card and posts it to X every morning. Your timeline finally looks like what you actually are — someone who ships. → 8 card designs, rotating (terminal, heatmap, flame, ticker…) so it never gets stale → weekly + monthly milestone cards — your streak becomes a story worth following → tweet from your CLI / Cursor / Claude Code without leaving your editor → free for 10 days, full access See who else is shipping daily under #proofofship — and join them. It touches your repo, so safe-to-try came first: → open source (AGPL) — audit it or self-host → read-only — we never touch your code This is my first build-in-public tool. I built it for myself, and for anyone tired of switching between shipping and posting about shipping. First 100 get founding lifetime — a permanent number on every card. Try it, tell me

@akhileshrangani · X

i built codex micro and used it inside of claude to control codex AND claude code it uses a herdr bridge that is running on my mac talks it through a ngrok proxy uses to render inside of claude

@marcin_u2 · X

-> here it is! claude finally knows everything gpt knows. and both of them know everything that's happened across your email, drive, slack, notion, github and granola :)

@raster_app · X

othmanosx · HN

I still don't like the fact that AI is adding more stuff for us to read, it's accelerating the code production but slowing down the code review. I built my own code reviewer as well ( https://pyor.review/ ), surfacing the important stuff first is the right track, but adding more stuff to read is daunting, but asking AI to just point you to what you need to focus on and skim the noise is what I'm leaning more towards.