Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Zot – Yet another coding agent harness

zot.sh

Post reply on HN
Print view View original

71–80 of 88 posts

Re: Show HN: Zot – Yet another coding agent harness

#71

Post by 0xbadcafebee »

Great minds think alike? Two months ago I created an agent called 'zop' [1] that's also a static Go app. It's not a code harness, it's a cli tool for quick one-liners (faster and less memory than opencode --prompt) with canned system messages. With compile tags you can strip it down to just prompt execution and the binary's less than 3MB.

....But also because feature creep, you can compile-in text-to-speech, speech-to-text, an interactive mode, an Android app, MCP/tool calling, multiple provider support, and now a really crappy web interface that only half works. It turns out vibe coding is harder/more time-consuming than it seems... Creating an alternative to beads made it more manageable, but I need multi-agent orchestration to code it so I don't have to babysit it and manually QA it (because just installing playwright and telling the AI to write tests doesn't really work).

Kind of a waste of time, but interesting learning experience. Now I know why there aren't a hundred magically awesome user tools out there... they're still not that easy to make.

[1] https://codeberg.org/mutablecc/zop

Re: Show HN: Zot – Yet another coding agent harness

#72

Post by dang »

sally_glance wrote: post #66
dang wrote: post #49

Since this project hasn't had much attention, I replaced the submitted title ("Zot now supports Claude Opus 4.8") with that of https://news.ycombinator.com/item?id=47931161 . I hope that's ok! (I also merged https://news.ycombinator.com/item?id=47941645 from that thread into this one)

Does that also merge view/vote metrics? I mean I could probably look it up in the source, but I'm lazy...

No.

Re: Show HN: Zot – Yet another coding agent harness

#73

Post by LoganDark »

lejalv wrote: post #31
LoganDark wrote: post #17

Earlier quoted context omitted.

I have not tried pi! I heard of it, but I didn't look into it because Anthropic is cracking down on third-party harnesses by making them prohibitively expensive. I suppose though now that I have a DeepSeek API key due to Reasonix I can give it a shot. (even the pro model is so cheap!! I've been using it for days on multiple projects and have barely spent $1, and I think it can go much further with better prompting.)…

No, I just was curious to know how you found Pi; I've got so much from pi + DS4 pro that I think I am done feeling bad about Anthropic limits. The cost is ridiculous, but I wonder if there's even a lower floor with reasonix or DS4-specific pi config

I saw Pi on the front page of Hacker News a few weeks ago, I think.

Anyway, I've been trying it for the past day or so and I must say, this is awesome. The extension functionality in particular is great news at least. But there's a lot more to love that seems to actually have been tastefully crafted by real people; a lot of power-user features that would fly right over most agentic implementers, such as branching on the level of individual tool calls rather than only by user messages as in Claude Code. It feels incredibly good, I am very happy with it.

Re: Show HN: Zot – Yet another coding agent harness

#75

Post by throwa356262 »

0xbadcafebee wrote: post #71

Great minds think alike? Two months ago I created an agent called 'zop' [1] that's also a static Go app. It's not a code harness, it's a cli tool for quick one-liners (faster and less memory than opencode --prompt ) with canned system messages. With compile tags you can strip it down to just prompt execution and the binary's less than 3MB. ....But also because feature creep, you can compile-in text-to-speech, speech-…

This looks really interesting!

Being a single binary with modest memory requirements, I wonder if it can be used as a voice assistant in somethings like a rpi.

Re: Show HN: Zot – Yet another coding agent harness

#76

Post by Terretta »

0gs wrote: post #45
patriceckhart wrote: post #43

Earlier quoted context omitted.

You rocking your own harness? Public by any chance? If so, mind if I take a look?

i am somebody else but my Show HN got zero engagement so please feel free to look at mine: http://github.com/0gsd/enough n.b. not a coding harness. it's for writing. but extensibility is a big (perhaps too big) part of it. http://enough.support has some of the principles outlined.

Here is some engagement: your project may be hard to engage with unless someone is highly motivated?

> "this is because `enough` imposes very few paradigms on your wordflows -- in a world of exponential possibility, most people have as many things they want to do as ways they prefer to do them."

OK, but, having read the GitHub and the reverse chronology discourse, but not doing the install, I cannot immediately tell what anyone's wordflow might be or whether this could be helpful in any way.

Usually from looking at a project I can imagine a venn diagram of things I want to do and things the thing does. Not here. Also, I felt I was pointed to principles, but rather than principles of the tools purpose, I found motivations for the author and meta comments about the discourse site itself, rather than motivations to use the tool or comments on its application to authoring assistance.

Rather than those, ironically the best entry point seems to be the agent guide:

https://github.com/0gsd/enough/blob/main/docs/AGENT_GUIDE_v0...

From there it appears you're trying to make a combination of humane/verbal human-driving-the-loop document reviser (e.g. the colored text visualizer and agentic tool to grab references by color for other tool consideration), and a substrate (cough) for arbitrary "paradigms" of working towards producing writing of a given "motivation". From there, one goes into the `defaults` to find translation and text planning paradigms:

https://github.com/0gsd/enough/blob/main/defaults/paradigms/...

https://github.com/0gsd/enough/blob/main/defaults/paradigms/...

While the spelunking approach can give the idea, is there any writeup anywhere that walks someone through the concept and an applied example from the POV of the human who made this?

I note non-ironically the text planner has no explainer in the example document types. :-)

Re: Show HN: Zot – Yet another coding agent harness

#77

Post by Terretta »

Mashimo wrote: post #19
cedws wrote: post #18

Glad to see tooling in my native language. I don’t want to touch TypeScript stuff with a ten foot pole, but sadly it seems to be the lingua franca for agentic tools. The one thing that would keep me from making the jump is CC’s auto mode.

> I don’t want to touch TypeScript stuff with a ten foot pole Why not? Is it because you need to change the code?

> Is it because you need to change the code?

Indeed! It would be difficult to deliberately design a more long-term-TCO-destructive ecosystem.

Effectively everything about it is "the one you throw away", and worse, effectively everyone uses it as if they're building the one to throw away.

Re: Show HN: Zot – Yet another coding agent harness

#78

Post by Terretta »

airbreather wrote: post #2

this is fucking awesome it is fast, there is no fucking gateway fuckaround or any other similar issues, up and going in seconds straight away I added two skills, that it wrote for itself, read my gmails and attachments, and browse the web, text browser first up, render page and screenshot with OCR for javascript heavy pages\ then I asked it, find the best value ram in my area, second hand as well as new, try gumtree…

What model behind all this?

Re: Show HN: Zot – Yet another coding agent harness

#79

Post by Terretta »

ignatif wrote: post #50

thank you for the honest description

This real world usage of LLM's favorite word shows why LLMs pair this word with "what I'm about to say is seriously unreliable".

Here, "honest description" means the author didn't make something out to be more than it is. Perfect.

Ironically, LLMs don't apply that to the thing they're describing, but to their description itself. Meaning: when they say "honestly" it flags they have no idea and are about to be lazy, make it up, and confidently assert nonsense.

It's easiest to understand if you mentally insert a phrase:

"Honestly [you should disregard this because I am just making this up but], you made a great choice."

Re: Show HN: Zot – Yet another coding agent harness

#80

Post by 0gs »

Terretta wrote: post #76
0gs wrote: post #45

Earlier quoted context omitted.

i am somebody else but my Show HN got zero engagement so please feel free to look at mine: http://github.com/0gsd/enough n.b. not a coding harness. it's for writing. but extensibility is a big (perhaps too big) part of it. http://enough.support has some of the principles outlined.

Here is some engagement: your project may be hard to engage with unless someone is highly motivated? > "this is because `enough` imposes very few paradigms on your wordflows -- in a world of exponential possibility, most people have as many things they want to do as ways they prefer to do them." OK, but, having read the GitHub and the reverse chronology discourse, but not doing the install, I cannot immediately tell…

extremely helpful! thank you. my real mind killer here is "everybody knows how a harness works" vs. "this is for people who don't know what 'harness' even means" and i need to figure out how to close that gap.
Post reply on HN