"Answer this question by only using the `semble` CLI (docs below):

> What tools does Browsercode provide to the agent other than the base OpenCode tools? Provide the exact schema for tool input and tool output and briefly summarize what they do and how they work

---

[the AGENTS.md snippet provided from https://github.com/MinishLab/semble#bash-integration]"

And the equivalent for the non-Semble test:

"Answer this question by only using the `rg` and `fd` CLIs:

> What tools does Browsercode provide to the agent other than the base OpenCode tools? Provide the exact schema for tool input and tool output and briefly summarize what they do and how they work"

In both cases, I used Pi with gpt-5.4 medium and a very minimal setup otherwise. (And yes, I did verify that either instance only used rg & fd, or only used semble.)

Without Semble, it used 10.9% of the model context and used $0.144 of API credits (or, at least, that's what Pi reported - I used this with a Codex sub so cannot be sure). With Semble, it used 9.8% of the model context and $0.172 of API credits. The resulting responses were also about the same. Very close!

I tried one more test in the OpenCode repo. The question was > Trace the path from 1) the OPENCODE_EXPERIMENTAL_EXA env var being set to to 1 to 2) the resulting effects in the system prompt or tool provided to the OpenCode agent.

And I included the same instructions/docs as above. The non-Semble version was a bit more detailed -- it went into whether the tool call path invoked Exa based on whether Exa or Parallel was enabled for the web search provider -- but w.r.t. actually answering the question, both versions were accurate. The Semble version used 14.7% context / $0.282 API cost, while the non-Semble version used 19.0% / $0.352. Clearly a win for Semble for context efficiency, but note that the non-Semble version finished about twice as fast as the Semble version.

Of course this is just me messing around. ymmv.

I think using the Pi coding agent really got me used to this way of thinking: https://mariozechner.at/posts/2025-11-30-pi-coding-agent/#to...

https://github.com/pasky/chrome-cdp-skill

For example, I use codex to manage a local music library, and it was able to use the skill to open a YT Music tab in my browser, search for each album, and get the URL to pass to yt-dlp.

Do note that it only works for Chrome browsers rn, so you have to edit the script to point to a different Chromium browser's binary (e.g. I use Helium) but it's simple enough

It's essentially a SolidStart SPA with virtualized scrolling and a few other tricks (even I don't know most of them!). Vector search is entirely client-side with transformers.js and CLIP. The first load is quite slow unfortunately, cause it has to download the index of photo id -> link (~7 mb last time i checked), and same for searches, as it has to download the vector index (~28mb) and embedding model the first time. Caching is pretty good though.

I was previously using [Lychee](https://lychee.electerious.com/), which worked well but wasn't really suited for this use case. So I scrapped it and started from first principles with Claude. This entire task only used up 50% of my 5-hour quota on the $20 plan!

Since the site itself is an SPA and images are static, using a VPS is overcomplicating things since I (well, Claude) am essentially just using Caddy as a glorified CDN. But I had free DigitalOcean credits since I'm a student, and where else can I host 40 gigabytes of photos for free?

All in all, this was definitely a very fun exploration of what someone who's technical[1] can do with Claude. The code is all open-source (but it's slop) at https://github.com/aadishv/catapp.

[1]: at least I'd like to consider myself technical!

Comments URL: https://news.ycombinator.com/item?id=47284763

Points: 20

# Comments: 11

Comments URL: https://news.ycombinator.com/item?id=46417697

Points: 3

# Comments: 0

"I hate GitHub because X Y and Z features are bad" is a good reason to move away; "I hate GitHub because one of their thousands of enterprise customers does not align with my political views" is not, in my opinion.

For the record, I do not support ICE

I daily drive Zed for work across several languages and I love it. I use a lot of its features, like the git interface, agentic editing, etc. I might even consider paying for Pro in the future if I want unlimited edit predictions.

However, all of these complaints are fully justified. I think Zed is a massive undertaking, only one that a VC-backed company has the capital to do. iirc, it requires 70k lines of Rust just for the cloud part [1]. I cannot fathom the amount of fundamental infrastructure they have to get the editor functional at all. That doesn't excuse all of the papercuts in Zed though.

If I were Zed I would do the following:

1. stop all work on future features, like DeltaDB etc. They all seem extremely cool but they won't meaningfully contribute to increasing Zed adoption or fixing its issues.

2. remove all agentic editing features. if Zed tries to simultaneously become the world's best agentic editor and a good general-purpose text editor, it will fail at both. Keep around ACP so users can still use other agents, but remove all of Zed's built in agent stuff.

3. fix literally every papercut. Triage every single issue and go through every PR, even if it will take half a year to do so. People won't switch to Zed until it's perfect, and the existence of this many issues means it's not perfect enough.

4. make extensions actually good. Every programming language, library, etc. has it's own ecosystem, and many such ecosystems mainly rely on VSCode extensions for advanced features. Zed needs to be extremely extensible like VSCode is; obviously its architecture makes this slightly harder, as it's nontrivial, for example, for extensions to render their own GUI, but there are a lot of low(er)-hanging fruit for extensions that need to get solved. People will only switch to Zed if they can get a similar breadth of ecosystems.

Of course, this won't happen, and given that none of these will really make them money, Zed has no incentive to focus on these, especially given the amount of time they would need to do this. But I think that if Zed can't nail the core experience, it won't get anywhere.

[1] https://maxdeviant.com/posts/2025/head-in-the-zed-cloud/