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

621–630 of 700 posts

Re: OpenCode – Open source AI coding agent

#621

Post by sebastianconcpt »

xpe wrote: post #519
sebastianconcpt wrote: post #503

OpenCode is the almost good IDE I need. What does well: helps context switching by using one window to control many repos with many worktrees each. What can do better? It's putting AI too much in control? What if I want to edit a function myself in the workspace I'm working on? or select a snippet and refer that in the promp? without that I feel it's missing a non-negotiable feature.

Do you think the design direction of “chat first” is compatible with editor first? I don’t know if any tools do both well. Seems like a fork in the road, design wise.

I think we already need to flow back and forth in both modes. Because you steer from the chat more ambitious changes (zoom out) but then you need to still have the power to go full high res and zoom in in whatever you need.

From architecture to system programming smoothly. We need to nail that.

Re: OpenCode – Open source AI coding agent

#622

Post by jmmv »

smugtrain wrote: post #594
jmmv wrote: post #374

Earlier 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…

On the 100% cpu issue, I’m curious to know, what is the processor and was it performing any other cpu intensive work?

I’m not sure why any of this matters? I was looking at top, and the only two non-idle processes were claude and codex.

Re: OpenCode – Open source AI coding agent

#623

Post by driftnode »

nunchiai wrote: post #300
girvo wrote: post #244

Earlier quoted context omitted.

> I’m sure we’ll all learn a lot from these early days of agentic coding. So far what I am learning (from watching all of this) is that our constant claims that quality and security matter seem to not be true on average. Depressingly.

I think what we're seeing is a phase transition. In the early days of any paradigm shift, velocity trumps stability because the market rewards first movers. But as agents move from prototypes to production, the calculus changes. Production systems need: - Memory continuity across sessions - Predictable behavior across updates - Security boundaries that don't leak The tools that prioritize these will win the enterpris…

[dead]

Re: OpenCode – Open source AI coding agent

#624

Post by EnPissant »

ctmnt wrote: post #409
jmmv wrote: post #374

Earlier 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…

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`…

That's the same reason I don't like Opencode, but Codex doesn't use the alternate screen. I remember it did when it was very very new, but now it doesn't.

Re: OpenCode – Open source AI coding agent

#625

Post by phainopepla2 »

epolanski wrote: post #349
krzyk wrote: post #319

Earlier quoted context omitted.

By "agent" you mean what? Coding is mostly "agentic" so I'm bit puzzled.

It's defined in opencode docs, but it's an overall cross industry term for custom system prompt with it's own permissions: https://opencode.ai/docs/agents/

I'm still kind of confused, but opencode itself comes with several agents built-in, and you can also build your own. So what does it mean to use opencode itself as an agent?

Re: OpenCode – Open source AI coding agent

#628

Post by thayne »

UltraSane wrote: post #344
igravious wrote: post #332

Earlier quoted context omitted.

Driver issues are way more of a thing on Windows than Linux or MacOS.

Getting hardware to work is MUCH harder on Linux

It depends. For a lot of hardware it's actually easier to get working on linux, because the driver is just part of the kernel and you don't have to do anything special, including manually installing drivers, to get it working.

There are some cases where hardware support on Linux is suboptimal, such as Nvidia cards and many fingerprint readers, but things are a LOT better now than they used to be. Most consumer laptops and desktops will run linux just fine.

Re: OpenCode – Open source AI coding agent

#629

Post by Andrei_dev »

Yokohiii wrote: post #482
kelipso wrote: post #468

Earlier quoted context omitted.

Even then, you still need to read that code and Rust is way less read friendly than Go.

I have the impression that most vibe coders don't read code. I guess they would probably use something accessible to them, just in case.

[flagged]
Post reply on HN