This is really cool!
Essentially version controlled A2A.
I'm exploring a bunch of agent protocols right now and experimenting with a similar concept for context syncing over git here: https://github.com/cjroth/csp
HN user
This is really cool!
Essentially version controlled A2A.
I'm exploring a bunch of agent protocols right now and experimenting with a similar concept for context syncing over git here: https://github.com/cjroth/csp
Updated!
Fair point :)
Thunderbolt was funded from a grant, not donations.
https://github.com/thunderbird/thunderbolt/blob/main/docs/fa...
It's not. Mozilla has been more than Firefox for a long time.
Hi, I'm on team that worked on this. No it's not vibe coded. We do pretty intense code review of every PR. It looks like the number you're seeing is including lock files and artifacts that are not part of the core coverage.
I think that wasn't phrased well- it's "revenue" positive meaning donation money covers more than the expenses
Stop spreading misinformation, it's funded by grant money https://github.com/thunderbird/thunderbolt/blob/main/docs/fa...
I've been experimenting with running Gemma with MLX directly within my own harness: https://github.com/cjroth/mlx-harness
I agree. Also, very different world from Rust, but shadcn has popularized this for UI components and AI skills are done this way frequently.
I'm excited to see more patterns like this for other types of code.
Websockets would work great actually! Basically anything would work as long as you don't use any node or bun specific imports. For file systems you could also use something like this https://github.com/isomorphic-git/lightning-fs
I'm glad you think the try before install scenario makes sense - I think this is definitely the main use case.
Yep, mainly performance - specifically page load time (near instant for Gridland vs ~2-3s for Ink Web). The other issue was flickering. Tbh rendering directly into a canvas is just a better approach and OpenTUI's architect is more modern.
I love that xkcd, I never know what to do, so I'll just :))
You should be able to. We forked OpenTUI in order to avoid having to shim a bunch of native stuff. I'd like to make it compatible - email me at hi@cjroth.com if you find a way or want any help making it work
Does anyone know if this is mainly going to affect people in Cary, NC?
Nice! I made a proof-of-concept of using Ink + Ghostty Web a few months back - we didn't end up merging it, but it's still an interesting thing that's possible. I think Ghostty Web is also has tons of potential.
Yes (if you're also down to use React)
Thank you! I'm glad you think so. It's all about fun.
There have been a lot of conversations recently about how model alignment is relative and diversity of alignment is important - see the recent podcast episode between Jack Clark (co-founder of Anthropic) and Ezra Klein.
Many comments here point out that Mistral's models are not keeping up with other frontier models - this has been my personal experience as well. However, we need more diversity of model alignment techniques and companies training them - so any company taking this seriously is valuable.
This is a fascinating report, not because of the content or even quality of the report, but because of the way it was generated. It is an AI generated report dumped into GitHub and has made it onto the front page of Hacker News with over 1,000 upvotes and many comments.
This type of GitHub-based open-source research project will become more common as more people use tools like Claude Code or Codex for research.
I agree, agents struggle with TUIs. I do think this is easy to fix though (here's an interesting approach: https://github.com/remorses/ghostty-opentui). I think agents will have much better luck with TUIs than browsers.
The more interesting scenario IMO is having apps that are both TUIs AND CLIs where the agent uses the CLI but can pause and show the user a TUI for complex tasks where the user needs to input something.
Theory: terminal apps are closing the agent self-improvement loop because agents can use TUIs more easily than web/desktop/mobile.
Anomaly, which builds OpenCode + OpenTUI), is also doing some really interesting stuff in this space with their custom renderer. And then there's Ink (https://github.com/vadimdemedes/ink) which is what Claude Code uses. I also built Ink Web (https://github.com/cjroth/ink-web) to make Ink work in the browser.
The virality of OpenClaw and Claude Code has me wondering if terminals could actually go mainstream (eg used by non-tech users). More thoughts here: https://www.cjroth.com/blog/2026-03-05-terminals-are-cool-ag...
Personally I love it. It just feels fast and minimal. I'm on Mac.
My team is building a cross platform app with Tauri that is mobile, web, and desktop in one codebase and we've had almost nothing bad to say. It's been great. Also the executable size and security are amazing. Rust is nice. Haven't done as much with it yet but it will come in useful soon as we plan to implement on-device AI models that are faster in Rust than WebGPU.
I'm glad I'm not the only one whose features are obsolete by the time they're ready to ship!
Feature request: renaming tabs! Helps keep tabs organized instead of 20 tabs with similar names. (See Zed for example)
Also! I'm considering Ghostty web (https://github.com/coder/ghostty-web) for my project Ink Web. It's awesome that Ghostty can work in the browser to replace xterm.js.
https://github.com/cjroth/ink-web/pull/1
Project: https://www.ink-web.dev/
I'm hacking on a similar thing that lets you build CLIs directly into xterm / ghostty web so that they also work in the terminal. Eg they are cross platform web and CLI.
Demo: https://wizard-nine-blush.vercel.app/
Project: https://ink-web.dev
I love the approach of just bash as well. Super cool!
Edit: warning - don't use it mobile.
A short philosophical essay.
~* There is no difference between a model that escapes its sandbox and a model that emulates escaping a sandbox.
Originally I posted this on LessWrong, but it's stuck in the moderation queue, so I thought I'd post it here too.
The people winning mostly had a head start. Or they have money. Usually both.
It feels like that doesn't it? But, as one counter-point, OpenClaw. :)
Btw I did a deep-dive into AI moats last week and wrote a blog post about it. Relationships were most likely the strongest moat from my research - but definitely having a large amount of money in reserves helps. https://www.cjroth.com/blog/2026-02-11-moats-in-the-age-of-a...
It could be smart for them to get in now with so much talk of a bubble or potential stock market correction.
I got ghostty-web working with this and it is great. Unfortunately it seems I don't have enough karma to post a link to it. But it's ink-web on npm if you're interested!
The nice thing about this is that you do not need an OS / backend of any kind - everything runs in the browser - similar to webcontainers but without even needing a container.