I'm a https://pi.dev man myself.
> Sessions are stored as trees
that is actually really nice
OpenCode – Open source AI coding agent
401–410 of 700 posts
Re: OpenCode – Open source AI coding agent
#402Earlier quoted context omitted.
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.
This. I work on projects that warrant a self hosted model to ensure nothing is leaked to the cloud. Imagine my surprise when I discovered that even though the only configured model is local, all my prompts are sent to the cloud to... generate a session title. Fortunately caught during testing phase.
[dead]
Re: OpenCode – Open source AI coding agent
#403Earlier quoted context omitted.
> and (partly as a result) it's fairly resource inefficient (often uses 1GB of RAM or more. For a TUI). That's (one of the reasons) why I'm favoring Codex over Claude Code. Claude Code is an... Electron app (for a TUI? WTH?) and Codex is Rust. The difference is tangible: the former feels sluggish and does some odd redrawing when the terminal size changes, while the latter definitely feels more snappy to me (leaving a…
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.
Re: OpenCode – Open source AI coding agent
#404The maintaining team is incredibly petty though. Tantrums when they weren't allowed to abuse Claude subscriptions and had to use the API instead. They just removed API support entirely.
‘abuse’. The same rate limits apply, the requests still go to the same endpoints. Even as a CC user I’m glad someone is forcing the discussion. My prediction: within two years ‘model neutrality’ will be a topic of debate. Creating lock-in through discount pricing is anti-competitive. The model provider is the ISP; the tool, the website.
> The same rate limits apply, the requests still go to the same endpoints.
That is not the point. That is a mere technicality.
You signed a contract. If you don't ignore the terms of the contract to use the product in a way that is explicitly prohibited, you're abusing the product. It is as simple as that.
They offer a separate product (API) if you don't like the terms of the contract.
Also, if you really want to get technical: the limits are under the assumption that caching works as intended, which requires control of the client. 3P clients suck at caching and increase costs. But that is not the overarching point.
> Creating lock-in through discount pricing is anti-competitive.
Literally everyone does this. OpenAI is doing this with Codex, far more than Anthropic is. It's not great but players much bigger than Anthropic are using discount pricing to create an anti-competitive advantage.
Re: OpenCode – Open source AI coding agent
#405The 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.
> You can't write your system prompt in opencode
Now I just started looking into OpenCode yesterday, but seems you can override the system prompts by basically overloading the templates used in for example `~/.opencode/agents/build.md`, then that'd be used instead of the default "Build" system prompt.
At least from what I gathered skimming the docs earlier, might not actually work in practice, or not override all of it, but seems to be the way it works.
Re: OpenCode – Open source AI coding agent
#406The maintaining team is incredibly petty though. Tantrums when they weren't allowed to abuse Claude subscriptions and had to use the API instead. They just removed API support entirely.
> we did our best to convince anthropic to support developer choice but they sent lawyers https://x.com/i/status/2034730036759339100
Anthropic has zero problems with API billing, there's no chance they told him to rip that out.
Reading through his X comments and GitHub comments he is behaving immaturely. I don't trust what he's saying here. Ripping out Claude API support was just throwing a tantrum. Weird given his age - he's old enough to be more mature.
Re: OpenCode – Open source AI coding agent
#407Earlier quoted context omitted.
You're both right. AI can be used to do either fast releases or well designed code. Don't say both, as you're not making time, you're moving time between those two. Which one you think companies prefer? Or if you're a consulting business, which one do you think your clients prefer?
> AI can be used to do either fast releases or well designed code I have yet to actually see a single example of the latter, though. OpenCode isn't an isolated case - every project with heavy AI involvement that I've personally examined or used suffers from serious architectural issues, tons of obvious bugs and quirks, or both. And these are mostly independent open source projects, where corporate interests are (hope…
> It's easy to say "just mindlessly follow X principle and your software will be good", where X is usually some variation of "just add more tests", "just add more agents", "just spend more time planning" etc
That's a complete strawman of what I — or others trying to learn how to use coding agents to increase quality, like Simon Willison or the Oxide team — am saying.
> but I choose to believe that good software cannot be created without the involvement of someone who has a passion for writing good software - someone who wouldn't want to let an LLM do the job for them in the first place.
This is just a no true Scotsman. I prefer to use coding agents because they don't forget details, or get exhausted, or overwhelmed, or lazy, or give up, ever — whereas I might. Therefore, they allow me to do all of the things that improve code and software quality more extensively and thoroughly, like refactors, performance improvements, and tests among other things (because yes, there is no single panacea). Furthermore, I do still care about the clarity, concision, modularity, referential transparency, separation of concerns, local reasonability, cognitive load, and other good qualities of the code, because if those aren't kept up a) I can't review the code effectively or debug things as easily when they go wrong, b) the agent itself will struggle to male changes without breaking other things, and struggle to debug, c) those things often eventually effect the quality of the end state software.
Additionally, what you say is empirically false. Many people who do deeply value quality software and code quality, such as the creators of Flask, Redis, and SerenityOS/Ladybird, all use and value agentic coding.
Just because you haven't seen good quality software with a large amount of agentic influence doesn't mean it isn't possible. That's very close minded.
Re: OpenCode – Open source AI coding agent
#408Earlier 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.
> It's more accessible to contributors.
What would make go more "accessible to contributors" than Rust?
Re: OpenCode – Open source AI coding agent
#409OpenCode 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…
> and (partly as a result) it's fairly resource inefficient (often uses 1GB of RAM or more. For a TUI). That's (one of the reasons) why I'm favoring Codex over Claude Code. Claude Code is an... Electron app (for a TUI? WTH?) and Codex is Rust. The difference is tangible: the former feels sluggish and does some odd redrawing when the terminal size changes, while the latter definitely feels more snappy to me (leaving a…
I think you’re confusing capital c Claude Code, the desktop Electron app, and lowercase c `claude`, the command line tool with an interactive TUI. They’re both TypeScript under the hood, but the latter is React + Ink rendered into the terminal.
The redraw glitches you’re referring to are actually signs of what I consider to be a pretty major feature, a reason to use `claude` instead of `codex` or `opencode`: `claude` doesn’t use the alternate screen, whereas the other two do. Meaning that it uses the standard screen buffer, meaning that your chat history is in the terminal (or multiplexer) scrollback. I much prefer that, and I totally get why they’ve put so much effort into getting it to work well.
In that context handling SIGWINCH has some issues and trickiness. Well worth the tradeoff, imo.
Re: OpenCode – Open source AI coding agent
#410Earlier 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.
agents don't really care and they're doing anywhere between 90-100% of the work on CC. if anything, rust is better as it has more built-in verification out of the box.