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

61–70 of 88 posts

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

#61

Post by unshavedyak »

> Subscription-capable - Anthropic Claude Pro/Max (anthropic), OpenAI Codex / ChatGPT Plus/Pro (openai-codex), Kimi Code (kimi), and GitHub Copilot (github-copilot).

Am i reading this right? Seems to suggest that this can be used with Claude Code Subscription, which isn't true i think. Did this pre-date the CC Subscription change? Or is it playing fast and loose with the rules hah.

Maybe it's using `-p`, which technically works for another few days i think lol. (That's going away.. what, June 1st? Something like that?)

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

#62

Post by varun_ch »

roxolotl wrote: post #51

Coding agent harnesses strike me as similar to blog generators. They can be as simple or as complex as you’d like. Plugins help with adoption. And if you want it’s real easy to write your own that does exactly what you want.

Isn’t practically all simple software like this?

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

#64

Post by popcorncowboy »

PufPufPuf wrote: post #58
dsrtslnd23 wrote: post #6

Earlier quoted context omitted.

Didn't they allow using oauth in custom harnesses for personal use (e.g. pi.dev)?

That changes every 2-3 days. The current stance is that only interactive mode of first party harnesses is covered under monthly plans, everything else is pay-as-you-go with monthly credit allowance equal to the plan price.

Though this is how it will stay, and it won't be changing back. Anthropic has understood clearly for a while that they need to capture the stack. They will subsidise Max for as long as they need to do this. All other off-stack usage will get pushed into per-token billing.

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

#65

Post by dh1011 »

unshavedyak wrote: post #61

> Subscription-capable - Anthropic Claude Pro/Max (anthropic), OpenAI Codex / ChatGPT Plus/Pro (openai-codex), Kimi Code (kimi), and GitHub Copilot (github-copilot). Am i reading this right? Seems to suggest that this can be used with Claude Code Subscription, which isn't true i think. Did this pre-date the CC Subscription change? Or is it playing fast and loose with the rules hah. Maybe it's using `-p`, which techni…

I have the same concern. Looks like they do include a disclaimer in the GitHub README, but not on zot.sh.

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

#66

Post by sally_glance »

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...

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

#67

Post by sally_glance »

unshavedyak wrote: post #61

> Subscription-capable - Anthropic Claude Pro/Max (anthropic), OpenAI Codex / ChatGPT Plus/Pro (openai-codex), Kimi Code (kimi), and GitHub Copilot (github-copilot). Am i reading this right? Seems to suggest that this can be used with Claude Code Subscription, which isn't true i think. Did this pre-date the CC Subscription change? Or is it playing fast and loose with the rules hah. Maybe it's using `-p`, which techni…

It does not use -p, but it does try to impersonate Claude when talking to the Anthropic API. Will they detect the difference in usage patterns and ban anyone who exploits them? Who knows.

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

#68

Post by triyambakam »

varun_ch wrote: post #62
roxolotl wrote: post #51

Coding agent harnesses strike me as similar to blog generators. They can be as simple or as complex as you’d like. Plugins help with adoption. And if you want it’s real easy to write your own that does exactly what you want.

Isn’t practically all simple software like this?

In a reductionist view yeah but blog generators and agent harnesses sit at a different spectrum than an EHR/Excel/whatever other insanely complex edge case ridden work you can think of

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

#69

Post by impulser_ »

jadbox wrote: post #53

Is there a good benchmark leaderboard between coding agents?

Harnesses aren't really going to change much of the performance on models like Opus, and GPT.

You literally can just give the model a bash tool and it will do just fine in fact it will most likely do better than majority of harnesses due to how well models are at bash.

The model do all the lifting. It really doesn't matter which harness you use.

Post reply on HN