Hacker News new | ask | show | jobs
by nylonstrung 9 days ago
The bigger point is that the codebase is hopelessly bloated by vibe coded features at this point, mirroring the same problems with Claude Code. And stability, performance, memory use have all gotten terrible.

I liked Opencode a lot previously but there's no doubt it's not well-written software. Pi has fully replaced it for me and there are quite a few newer options that learned from Opencode and exercise more minimalism where it matters

5 comments

I keep seeing these conceptual complaints about OpenCode but it's unreasonably effective, so it's difficult to justify any time spent in changing to something else.

It hardly matters that it's vibe coded and ugly if it works well... and it does (for me).

Saving a few CPU cycles and reducing RAM utilization on my local system isn't going to meaningfully improve anything in and of itself; the wall time is all bounded by the model or by the code it's invoking (i.e. compiling or running the test suite).

Got a link? Pi is suitably as to make search engines questionable
For the future, adding the related concepts/themes around hard to search for terms tend to do the trick. Instead of searching "go" for example, do "go programming language". Or instead of "pi", do "pi agent" or even "pi llm".
Why should the default be for me to guess in a search engine more expertly when someone is referencing a program as a suggestion instead of for them to be more explicit? I get it for things that dont live on the web but if you are going to say you replaced some program with another program the default should really be to link it especially when the name is two common characters in a common order or it is opensource imo...
> Why should the default be for me

It doesn't have to be, of course. But if you're bothered by something in general in life, and there are two approaches to solving the problem, one that involves others doing the "right thing", or another that involves you changing your approach to it, then usually the latter is much easier to actually address, than the former, as it relies on changing the behaviour of a ton of people.

It's just a tip to make things easier for yourself, without needing others to change. Still, you can do things however you like to, no one is forced to do anything :)

While this is a generally useful suggestion you are giving, for Go in specific you can just use "golang".

All of the major search engines have understood that as a stand-in for "Go the programming language" for many years.

Yeah. That is a sore point.

It has overridden a 4000 year old strategy board game played by millions (mostly Asians).

"golang" is literally "Go language". Doesn't matter that it's one word.
pi.dev
If you are interested in truly battle tested one, check this https://ante.run/start/philosophy
I am on this trajectory too; opencode got me started but I tried to understand the way it is working and to do that I would normally read the source code, but the source code is really not fun.
This seems to be quite common. You start with OpenCode (assuming you're someone who skips all the Claude Code hype); then you start thirsting for more, and switch to oh-my-pi.

I generally view the kind of code in projects like OpenCode to be the same as binary machine code, and the harness that works on it is the compiler. The source code is the prompts (I guess), except we live in a weird state now we use the existing machine code + more prompts to make even more machine code.

Yeah, this has been my progression as well. Maybe next it'll be just using plain pi when you figured out exactly what you want from omp and what you don't
I like how browser and websearch is handled in omp. But I only like these two features, it might be time for me to actually spend some time with pi
No one here started with Aider? Or even text-generation-webui? Or SillyTavern? Or were they too pseudo-agentic? :)
Can you name a few? I'm looking for alternatives
OpenAI's Codex tool is not limited to only calling their models. You can create a profile that uses any OpenAI API compatible endpoint.

It's written in Rust. It seems to perform well. It also seems (from my poking around in it) on the whole well and deliberately written. It doesn't consume memory like a mf'er like Claude Code. It doesn't sit and chew background CPU like I've seen opencode.

I suspect it will accumulate more specific-to-OpenAI-isms over time though.

Pi or Dirge
write your own using pi.