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

351–360 of 700 posts

Re: OpenCode – Open source AI coding agent

#351

Post by epolanski »

01100011 wrote: post #220

Stupid question, but are there models worth using that specialize in a particular programming language? For instance, I'd love to be able to run a local model on my GPU that is specific to C/C++ or Python. If such a thing exists, is it worth it vs one of the cloud-based frontier models? I'm guessing that a model which only covers a single language might be more compact and efficient vs a model trained across many lan…

My own experience trying many different models is that general intelligence of the model is more important.

If you want it to stick to better practices you have to write skills, provide references (example code it can read), and provide it with harnessing tools (linters, debuggers, etc) so the agent can iterate on its own output.

Re: OpenCode – Open source AI coding agent

#352

Post by plastic3169 »

msh wrote: post #340
plastic3169 wrote: post #318

Earlier quoted context omitted.

I’ve been testing opencode and it feels TUI in appearance only. I prefer commandline and TUIs and in my mind TUI idea is to be low level, extremely portable interface and to get out of the way. Opencode does not have low color, standard terminal theme so had to switch to a proper terminal program. Copy paste is hijacked so I need to write code out to file in order to get a snippet. The enter key (as in the return by…

I don’t think good TUI’s are the same as good command line programs. Great tui apps would to me be things like Norton/midnight commander, borlands turbo pascal, vim, eMacs and things like that

Yes cli and tui are not the same, but I expect TUI to work decent in general terminal emulator and not acitvely block copying and pasting. Having to install supported terminal emulator goes against the vibe.

Re: OpenCode – Open source AI coding agent

#353

Post by brabel »

mattmanser wrote: post #335
causal wrote: post #238

Earlier quoted context omitted.

I've gotta say, it shows. Claude Code has a lot of stupid regressions on a regular basis, shit that the most basic test harness should catch.

I feel like our industry goes through these phases where there's an obvious thought leader that everyone's copying because they are revolutionary. Like Rails/DHH was one phase, Git/GitHub another. And right now it's kinda Claude Code. But they're so obviously really bad at development that it feels like a MLM scam. I'm just describing the feeling I'm getting, perhaps badly. I use Claude, I recommended Claude for the…

There are plenty of competitors! I’ve been using Copilot, RovoCLI, Gemni, and there’s OpenAI thing.

Re: OpenCode – Open source AI coding agent

#354

Post by vbernat »

heavyset_go wrote: post #258
rbehrends wrote: post #147

Earlier quoted context omitted.

I am more concerned about their, umm, gallant approach to security. Not only that OpenCode is permissive by default in what it is allowed to do, but that it apparently tries to pull its config from the web (provider-based URL) by default [1]. There is also this open GitHub issue [2], which I find quite concerning (worst case, it's an RCE vulnerability). [1] https://opencode.ai/docs/config/#precedence-order [2] https:…

It also sends all of your prompts to Grok's free tier by default, and the free tier trains on your submitted information, X AI can do whatever they want with that, including building ad profiles, etc. You need to set an explicit "small model" in OpenCode to disable that.

From the code, this does not seem to be true anymore. It falls back to the current model if no small model is identified with the current provider. https://github.com/anomalyco/opencode/blob/9b805e1cc4ba4a984...

Re: OpenCode – Open source AI coding agent

#355

Post by mrln »

woctordho wrote: post #193
rbehrends wrote: post #147

Earlier quoted context omitted.

I am more concerned about their, umm, gallant approach to security. Not only that OpenCode is permissive by default in what it is allowed to do, but that it apparently tries to pull its config from the web (provider-based URL) by default [1]. There is also this open GitHub issue [2], which I find quite concerning (worst case, it's an RCE vulnerability). [1] https://opencode.ai/docs/config/#precedence-order [2] https:…

RCE is exactly the feature of coding agents. I'm happy with it that I don't need to launch OpenCode with --dangerously-skip every time.

No, it is still configurable. You can specify in your opencode.json config that it should be able to run everything. I think they just argued that it shouldn't be the default. Which I agree with.

Re: OpenCode – Open source AI coding agent

#356

Post by brabel »

sorentwo wrote: post #327
logicprog wrote: post #107

OpenCode was the first open source agent I used, and my main workhorse after experimenting briefly with Claude Code and realizing the potential of agentic coding. Due to that, and because it's a popular an open source alternative, I want to be able to recommend it and be enthusiastic about it. The problem for me is that the development practices of the people that are working on it are suboptimal at best; they're con…

The moment that OpenCode, after helping fix a Dockerfile issue, decided it was time to deploy to prod without asking for consent , I was out.

You must never rely on AI itself for authorization… don’t let it run on an environment where it can do that. I can’t believe this needs to be said but everyone seems to have lost their mind and decided to give all their permissions away to a non deterministic thing that when prompted correctly will send it all out to whoever asks it nicely.

Re: OpenCode – Open source AI coding agent

#358

Post by Imustaskforhelp »

logicprog wrote: post #107

OpenCode was the first open source agent I used, and my main workhorse after experimenting briefly with Claude Code and realizing the potential of agentic coding. Due to that, and because it's a popular an open source alternative, I want to be able to recommend it and be enthusiastic about it. The problem for me is that the development practices of the people that are working on it are suboptimal at best; they're con…

I tried running Opencode on my 7$/yr 512mb vps but it had the OOM issue and yes it needs 1GB of ram or more.

I then tried running other options like picoclaw/picocode etc but they were all really hard to manage/create

The UI/UX I want is that I can just put my free openrouter api key in and then I am ready to go to get access to free models like Arcee AI right now

After reading your comments/I read this thread, I tried crush by charmbracelet again and it gives the UI/UX that I want.

I am definitely impressed by crush/ the charm team. They are on HN and they work great for me, highly recommended if you want something which can work on low constrained devices

I do feel like Charm's TUI's are too beautiful in the sense that running a connection over SSH can delay so when I tried to copy some things, the delay made things less copy-able but overall, I think that I am using Crush and I am happy for the most part :-)

Edit: That being said, just as I was typing this, Crush took all the Free requests from Openrouter that I get for free so it might be a bit of minor issue but overall its not much of an issue from Crush side, so still overall, my point is that Crush is worth checking out

Kudos to the CharmBracelet team for making awesome golang applications!

Re: OpenCode – Open source AI coding agent

#359

Post by taosx »

epolanski wrote: post #347
taosx wrote: post #299

The only thing I'm wondering is if they have eval frameworks (for lack of a better word). Their prompts don't seem to have changed for a while and I find greater success after testing and writing my own system prompts + modification to the harness to have the smallest most concise system prompt + dynamic prompt snippets per project. I feel that if you want to build a coding agent / harness the first thing you should…

You can't write your system prompt in opencode, there's no API to override the default anthropic.txt as far as I'm aware. I considered creating a PR for that, but found that creating new agents instead worked fine for me.

I've forked it locally, to be honest I haven't merged upstream in a while as I haven't seen any commits that I found relevant and would improve my usage, they seem to work on the web and desktop version which I don't use.

The changes I've made locally are:

- Added a discuss mode with almost on tools except read file, ask tool, web search only based no heuristics + being able to switch from discuss to plan mode.

Experiments:

- hashline: it doesn't bring that much benefit over the default with gpt-5.4.

- tried scribe [0]: It seems worth it as it saves context space but in worst case scenarios it fails by reading the whole file, probably worth it but I would need to experiment more with it and probably rewrite some parts.

The nice thing about opencode is that it uses sqlite and you can do experiments and then go through past conversation through code, replay and compare.

[0] https://github.com/sibyllinesoft/scribe

Post reply on HN