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

OpenCode – Open source AI coding agent

opencode.ai

Post reply on HN
Print view View original

361–370 of 700 posts

Re: OpenCode – Open source AI coding agent

#361

Post by zingar »

movq wrote: post #339
kuboble wrote: post #310

Earlier quoted context omitted.

? The whole idea of a coding assistant is to send all your interactions with the program to the llm model.

To the provider you select in the UI, I agree. But OpenCode automatically sends prompts to their free "Zen" proxy, even without choosing it in the UI. Imagine someone using it at work, where they are only allowed to use a GitHub Copilot Business subscription (which is supported in OpenCode). Now they have sent proprietary code to a third party, and don't even know they're doing it.

This is exactly me considering what I might have leaked to god knows who via grok. I was hyped by opencode but now I’m thinking of alternatives. A huge red flag… at best irresponsible?

Re: OpenCode – Open source AI coding agent

#362

Post by KronisLV »

anonym29 wrote: post #63
KronisLV wrote: post #55

Earlier quoted context omitted.

With Anthropic, you either pay per token with an API key (expensive), or use their subscription, but only with the tools that they provide you - Claude, Claude Cowork and Claude Code (both GUI and CLI variants). Individuals generally get to use the subscriptions, companies, especially the ones building services on top of their models, are expected to pay per token. Same applies to various third party tools. The belie…

>or perhaps to route certain requests to Haiku or Sonnet instead of using Opus for everything, to cut down on the compute You can point Claude Code at a local inference server (e.g. llama.cpp, vLLM) and see which model names it sends each request to. It's not hard to do a MITM against it either. Claude Code does send some requests to Haiku, but not the ones you're making with whatever model you have it set to - these…

Sounds pretty sane, the same way how OpenWebUI and probably other software out there also has a concept of “tool models”, something you use for all the lower priority stuff.

Actually curious to hear what others think about why Anthropic is so set on disallowing 3rd party tools on subscriptions.

Re: OpenCode – Open source AI coding agent

#364

Post by zingar »

heavyset_go wrote: post #257

By default OpenCode sends all of your prompts to Grok's free tier to come up with chat summaries for the UI. To change that, you need to set a custom "small model" in the settings.

Geez there should be a big warning on the tin about this. They’re so neatly integrated with copilot that I assumed (and told others) that they had all the privacy guarantees of copilot :(

Re: OpenCode – Open source AI coding agent

#365

Post by flexagoon »

nacs wrote: post #223
flexagoon wrote: post #77

Earlier quoted context omitted.

You can scroll down literally two messages in the Github issue you linked: > there isnt any telemetry, the open telemetry thing is if you want to get spans like the ai sdk has spans to track tokens and stuff but we dont send them anywhere and they arent enabled either > most likely these requests are for models.dev (our models api which allows us to update the models list without needing new releases)

You should really look at the 2nd link, its much worse than telemetry.. > opencode will proxy all requests internally to https://app.opencode.ai > There is currently no option to change this behavior, no startup flag, nothing. You do not have the option to serve the web app locally, using `opencode web` just automatically opens the browser with the proxied web app, not a true locally served UI. > https://github.com/a…

That is the address of their hosted WebUI which connects to an OpenCode server on your localhost. Would be nice if there was an option to selfhost it, but it is nowhere near as bad as "proxying all requests".

Re: OpenCode – Open source AI coding agent

#366

Post by the_mitsuhiko »

krzyk wrote: post #295
hippycruncher22 wrote: post #61

I'm a https://pi.dev man myself.

Why most of those tools are written in js/ts? JS is not something that was developed with CLI in mind and on top of that that language does not lend itself to be good for LLM generation as it has pretty weak validation compared to e.g. Rust, or event C, even python. Not to mention memory usage or performance.

In pi’s case there is a plugin system. It’s much easier to make a self extending agent work with Python or JavaScript than most other languages. JavaScript has the benefit that it has a great typing system on top with TypeScript.

Re: OpenCode – Open source AI coding agent

#367

Post by krzyk »

manmal wrote: post #308
krzyk wrote: post #295

Earlier quoted context omitted.

Why most of those tools are written in js/ts? JS is not something that was developed with CLI in mind and on top of that that language does not lend itself to be good for LLM generation as it has pretty weak validation compared to e.g. Rust, or event C, even python. Not to mention memory usage or performance.

For a TUI agent, runtime performance is not the bottleneck, not by far. Hackability is the USP. Pi has extensions hotreloading which comes almost for free with jiti. The fact that the source is the shipped artifact (unlike Go/Rust) also helps the agent seeing its own code and the ability to write and load its own extensions based on that. A fact that OpenClaw’s success is in part based on IMO. I can’t find the tweet…

OK, make sense, but there are also claw clones that are in Rust (and self modifying).

Also python ones would also allow self modifying. I'm always puzzled (and worried) when JS is used outside of browsers.

I'm biased as I find JS/TS rather ugly language compared to anything other basically (PHP is close second). Python is clean, C has performance, Rust is clean and has performance, Java has the biggest library and can run anywhere.

Re: OpenCode – Open source AI coding agent

#368

Post by systima »

james2doyle wrote: post #110
systima wrote: post #108

Open Code has been the backbone of our entire operation (we used Claude Code before it, and Cursor before that). Hugely grateful for what they do.

What caused the switch? Also, are you still trying to use Claude models in OpenCode?

Sorry, I missed part of your question:

What caused the switch was that we're building AI solutions for sometimes price-conscious customers, so I was already familiar with the pattern of "Use a superior model for setting a standard, then fine-tuning a cheaper one to do that same work".

So I brought that into my own workflows (kind of) by using Opus 4.6 to do detailed planning and one 'exemplar' execution (with 'over documentation' of the choices), then after that, use Opus 4.6 only for planning, then "throw a load of MiniMax M2.5s at the problem".

They tend to do 90% of the job well, then I sometimes do a final pass with Opus 4.6 again to mop up any issues, this saves me a lot of tokens/money.

This pattern wasn't possible with Claude Code, thus my move to Open Code.

Re: OpenCode – Open source AI coding agent

#369

Post by KronisLV »

blks wrote: post #345
siddboots wrote: post #159

Earlier quoted context omitted.

Openclaw has 20k commits, almost 700k lines of code, and it is only four months old. I feel confident that that sort of code base would have a no coherent architecture at all, and also that no human has a good mental model of how the various subsystems interact. I’m sure we’ll all learn a lot from these early days of agentic coding.

I’m learning that projects, developed with the help of agents, even when developers claim that they review and steer everything, ultimately are not fully understood or owned by the developers, and very soon turns into a thousand reinvented wheels strapped together by tape.

> very soon turns into a thousand reinvented wheels strapped together by tape.

Also most of the long running enterprise projects I’ve seen - there was one that had been around for like 10 years and like about 75% of the devs I hadn’t even heard of and none of the original ones were in the project at all.

The thing had no less than three auditing mechanisms, three ways of interacting with the database, mixed naming conventions, like two validation mechanisms none of which were what Spring recommended and also configurations versioned for app servers that weren’t even in use.

This was all before AI, it’s not like you need it for projects to turn into slop and AI slop isn’t that much different from human slop (none of them gave a shit about ADRs or proper docs on why things are done a certain way, though Wiki had some fossilized meeting notes with nothing actually useful) except that AI can produce this stuff more quickly.

When encountered, I just relied on writing tests and reworking the older slop with something newer (with better AI models and tooling) and the overall quality improved.

Re: OpenCode – Open source AI coding agent

#370

Post by ajb »

danielovichdk wrote: post #297
heavyset_go wrote: post #264

Earlier quoted context omitted.

We're still in the very early days of generative AI, and people and markets are already prioritizing quality over quantity. Quantity is irrelevant when it comes value. All code is not fungible, "irreverent code that kinda looks okay at first glance" might be a commodity, but well-tested, well-designed and well-understood code is what's valuable.

Generative what? Code is not a thing anymore, in fact it never really was, but now it's definitely not. Code today can be as verbose and ugly as ever, because from here on out, fewer people are going to read it, understand and care about it. What's valuable, and you know this I think, is how much money your software will sell for, not how fine and polished your code is. Code was a liability. Today it's a liability th…

You may not need to read it, but you still need to test it.

Code that has not been thoroughly tested is a greater liability, not a lesser one.l, the faster you can write it.

Post reply on HN