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

571–580 of 700 posts

Re: OpenCode – Open source AI coding agent

#571

Post by maleldil »

theshrike79 wrote: post #553
solarkraft wrote: post #522

Earlier quoted context omitted.

pnpm is amazing for speed and everybody should use it! but even with npm before it, at least it was correct . I had very few (none?) mysterious issues with it that could only be solved by nuking the entire environment. That is more than I can say about the python package managers before uv.

uv + PEP723 is amazing for CLI tools You download one .py, run it and uv automatically downloads and installs any requirements to a virtual environment and runs it

Has the developer tooling been fixed? Doesn't it use an ephemeral environment? How do editors/LSPs know where to get dependency information?

Re: OpenCode – Open source AI coding agent

#572

Post by UltraSane »

freehorse wrote: post #435
cracki wrote: post #375

Earlier quoted context omitted.

Users of MacOS rarely have an active dislike for Windows, nor are they likely to announce this.

I use macos and I do actively dislike windows: here I announce it.

I use windows and absolutely hate the mac UI. Having the current window title bar always at the top of the screen doesn't make any sense when you have a very big monitor. It only made sense with the tiny monitors available when the mac UI was originally created.

Re: OpenCode – Open source AI coding agent

#573

Post by thayne »

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…

That sounds a lot like my experience with claude code. IDK about OpenCode, but claude code is also largely written by LLMs, and you can tell.

Re: OpenCode – Open source AI coding agent

#574

Post by jy-tan »

jee599 wrote: post #371

[flagged]

I created a tool for this: https://github.com/Use-Tusk/fence

Same thoughts - I wanted a "permission manager" that defines a set of policies agnostic to coding agents. It also comes with "monitor mode" that shows operations blocked, but not quite an audit log yet though.

Re: OpenCode – Open source AI coding agent

#575

Post by fuy »

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…

claude code easily uses 10+GB in single session :) 1Gb sounds very efficient by comparison

Re: OpenCode – Open source AI coding agent

#576

Post by thayne »

seunosewa wrote: post #403
petcat wrote: post #396

Earlier quoted context omitted.

Anthropic needs to spend some tokens rewriting Claude Code in Rust (yes, really). The difference in feel between Codex and Claude Code is obvious. The whole thing is vibed anyway, I'm sure they could get it done in a week or two for their quality standards.

I'd suggest Go ahead of Rust. It's more accessible to contributors.

I think go will make it easier for more developers to contribute, bit rust would probably attract higher quality contributions.

Re: OpenCode – Open source AI coding agent

#577

Post by sam0x17 »

seunosewa wrote: post #403
petcat wrote: post #396

Earlier quoted context omitted.

Anthropic needs to spend some tokens rewriting Claude Code in Rust (yes, really). The difference in feel between Codex and Claude Code is obvious. The whole thing is vibed anyway, I'm sure they could get it done in a week or two for their quality standards.

I'd suggest Go ahead of Rust. It's more accessible to contributors.

If anything, the stricter the compiler the better for vibe coding the language

Re: OpenCode – Open source AI coding agent

#578

Post by BenGosub »

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 agree that Opencodr is using a lot of RAM, but regarding the features, I am ak only using the built in features and I wouldn't say they are too many, they are just enough for a complete workflow. If you need more you can install plugins, which I haven't done yet and it's my daily driver for four months.

Re: OpenCode – Open source AI coding agent

#579

Post by stavros »

AlexCoventry wrote: post #566
stavros wrote: post #329

Earlier quoted context omitted.

Anthropic was fine doing the same, they just didn't want it done to Americans.

OpenAI agreeing to operate as Trump's secret police materially impacts your security as a European, though, because it cements Trump's power.

Again, though, both of them agreed to that. Anthropic just didn't want to spy on Americans.

Re: OpenCode – Open source AI coding agent

#580

Post by kmod »

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.

Fwiw this got changed about a week ago, where they changed the logic to match the documentation rather than default to sending your prompts to their servers. This is why so many people have noticed this happening but if you ask an AI about it right now it will say this is not true.

Personally I think it's necessary to run opencode itself inside a sandbox, and if you do that you can see all of the rejected network calls it's trying to make even in local mode. I use srt and it was pretty straightforward to set up

Post reply on HN