Kiro: A new agentic IDE • Hacker News Board

Re: Kiro: A new agentic IDE

#461

Post by postalcoder » Wed, Jul 16, 2025, 1:14 AM UTC

re5i5tor wrote: post #178

postalcoder wrote: post #41

Earlier quoted context omitted.

I don't know if this is feedback for Kiro per se or more feedback for this category of applications as a whole, but I've personally noticed that the biggest barrier holding me back from giving an earnest look at new coding agents are the custom rules I've set up w/ my existing agents. I have extensively used Copilot, Continue, Cursor, Cline, Aider, Roo Code, and Claude Code. I've just finished porting my rules over t…

Not Kiro related, but do your Claude Code version of rules end up as CLAUDE.md files in various locations?

so I started off by doing this - having a single claude.md file but in it putting references to paths to other instruction files.

I found this approach to be quite poor from the standpoint of cloud seems to treat user instructions very differently than other agentic code assistants and I think it’s because their system prompt is so long. As a result, I’m getting some pretty poor adherence to my claude.md file and I’ve noticed that very rarely if ever have I seen it reverse the file to any of the nested paths.

So.. im going to try to refactor my files to keep it all in the same file, with some heavy “LOOK AT ME” prompt engineering.

How about you?

Re: Kiro: A new agentic IDE

#462

Post by nsonha » Wed, Jul 16, 2025, 2:10 AM UTC

yencabulator wrote: post #430

nsonha wrote: post #421

Earlier quoted context omitted.

Claude Code is what it is because of Claude, TUI or not isn't really the point. What makes IDEs lose to TUIs is that the agentic models can really do more than coding and is evolving toward a hands-off kind of workflow. A clunky IDE is too much for that, but TUI is not the way either. When has TUI ever been mainstream? Agentic tools of the future will be rich notebook/chat interface that's available in all form facto…

You can have an agent loop in your IDE, I don't see why anything makes "IDEs lose to TUIs" there. If anything, TUIs are the awkward in-between of "human in the loop, but with poor tools" where one side is fully automatic, agents suggesting fixes on issue tracker, and the other is holding-AI's-hand where you review every step one at a time. I hate trying to copy paste in/out of Claude Code's unnecessarily-cute boxed t…

I use the TUI for a lot of agentic stuff that is not necessarily coding, from performing some cloud management commands or just dumb things like "where the hell did I alias vim to nvim?". For those things, having to reach out to the IDE is annoying.

And the way I see the future of coding is that should should be able to code from anywhere, mobile, web, your computer. You already have your code on the cloud (most of the time). Neither TUI or IDE works well currently for that.

Re: Kiro: A new agentic IDE

#463

Post by kjsingh » Wed, Jul 16, 2025, 2:31 AM UTC

suralind wrote: post #46

angelmm wrote: post #28

Many companies are considering IDEs the way to reach developers. Atom started the trend of next generation IDEs and VSCode consolidated most of the market. With the AI raising, people are looking to get usage, gathering data, and positioning models. An IDE provides you all of that. AI seems to be a way to engage happy users to try new things. Kiro joins a growing list of projects: - Kiro (AWS) - VSCode + Copilot (Mic…

I love Zed as an editor/IDE without ANY AI/LLM features. I think the AI support in Zed is actually pretty decent and I'm still using it out of habit (actively trying to use more TUI for AI). But at the same time, it's my biggest worry that they will continue on the AI and pollute the project with too much junk. I gotta trust the smart minds behind it will find a way to balance this trend.

I am disappointed at Java support in Zed

Re: Kiro: A new agentic IDE

#464

Post by didibus » Wed, Jul 16, 2025, 2:47 AM UTC

touristtam wrote: post #413

SyrupThinker wrote: post #197

Earlier quoted context omitted.

That sounds too good to be true, and it seems like they are indeed introducing a usage system similar to their competitors next month? > Starting August 1, 2025, we’re introducing a new pricing plan for Amazon Q Developer designed to make things simpler and more valuable for developers. > Pro Tier: Expanded limits $19/mo. per user > 1,000 agentic requests per month included (starting 8/1/2025) - https://aws.amazon.co…

50 request per month? Am I reading that correctly? If that's the case it is pityful.

That's on the free plan. It's 1000 on the 19$ subscription, or 3000 on the 39$ one.

If you go over the limit, it's $.04 / request.

Re: Kiro: A new agentic IDE

#465

Post by didibus » Wed, Jul 16, 2025, 2:52 AM UTC

smcleod wrote: post #448

didibus wrote: post #334

Earlier quoted context omitted.

That's for the shell auto-complete feature which I turn off.

It's not that simple: https://github.com/aws/amazon-q-developer-cli/issues/844

This seems to only be impacting if you have the shell integration configured no?

I don't have the hooks installed and the integration is disabled. I'm only using the q command for agentic coding, not for shell auto-complete.

Re: Kiro: A new agentic IDE

#466

Post by nsonha » Wed, Jul 16, 2025, 4:52 AM UTC

kaptainscarlet wrote: post #406

esafak wrote: post #225

Earlier quoted context omitted.

There should be a standard rule format in a standard place, like ~/.config/llms/rules.md

.vibecodingrc sounds better?

do we want to make "vibe code" the umbrella term for llm, agents or even AI assisted software engineering? I think not.

Re: Kiro: A new agentic IDE

#467

Post by jetslab » Wed, Jul 16, 2025, 7:55 AM UTC

hey, the Kiro hangs on the login page and doesn't redirect

It hangs on "we will take you to the default browser to sign in and bring you back when it's complete"

I am using Linux Mint, I can see some errors in the console I am not sure if the have something to do with it ``` 2workbench.desktop.main.js:2188 Got token path with schema file and path /home/jc/.aws/sso/cache/kiro-auth-token.json workbench.desktop.main.js:35 INFO Started local extension host with pid 7545. workbench.desktop.main.js:10906 AI generated workspace trust dialog contents not available. (anonymous) @ workbench.desktop.main.js:10906 workbench.desktop.main.js:35 INFO [perf] Render performance baseline is 40ms workbench.desktop.main.js:35 INFO Extension host (LocalProcess pid: 7545) is unresponsive. workbench.desktop.main.js:10959 Extension host (LocalProcess pid: 7545) terminated unexpectedly. Code: 132, Signal: unknown xb @ workbench.desktop.main.js:10959 workbench.desktop.main.js:35 ERR Extension host (LocalProcess pid: 7545) terminated unexpectedly. The following extensions were running: kiro.kiroAgent, vscode.git-base workbench.desktop.main.js:35 INFO Automatically restarting the extension host. workbench.desktop.main.js:35 ERR Canceled: Canceled at Dy (vscode-file://vscode-app/usr/share/kiro/resources/app/out/vs/workbench/workbench.desktop.main.js:7:1004) at vscode-file://vscode-app/usr/share/kiro/resources/app/out/vs/workbench/workbench.desktop.main.js:10952:38456 at Array.forEach () at iht.dispose (vscode-file://vscode-app/usr/share/kiro/resources/app/out/vs/workbench/workbench.desktop.main.js:10952:38396) at WCe.dispose (vscode-file://vscode-app/usr/share/kiro/resources/app/out/vs/workbench/workbench.desktop.main.js:10952:50088) at XMs.dispose (vscode-file://vscode-app/usr/share/kiro/resources/app/out/vs/workbench/workbench.desktop.main.js:10959:7303) at JMs.stopAllInReverse (vscode-file://vscode-app/usr/share/kiro/resources/app/out/vs/workbench/workbench.desktop.main.js:10959:6605) at async Kot.rb (vscode-file://vscode-app/usr/share/kiro/resources/app/out/vs/workbench/workbench.desktop.main.js:10958:15546) workbench.desktop.main.js:35 ERR Canceled: Canceled at new OMs (vscode-file://vscode-app/usr/share/kiro/resources/app/out/vs/workbench/workbench.desktop.main.js:10952:36975) at iht.U (vscode-file://vscode-app/usr/share/kiro/resources/app/out/vs/workbench/workbench.desktop.main.js:10952:41622) at n..o.charCodeAt.n. (vscode-file://vscode-app/usr/share/kiro/resources/app/out/vs/workbench/workbench.desktop.main.js:10952:39111) at DYi.getSessions (vscode-file://vscode-app/usr/share/kiro/resources/app/out/vs/workbench/workbench.desktop.main.js:653:61586) at X4e.getSessions (vscode-file://vscode-app/usr/share/kiro/resources/app/out/vs/workbench/workbench.desktop.main.js:653:60310) at X4e.getAccounts (vscode-file://vscode-app/usr/share/kiro/resources/app/out/vs/workbench/workbench.desktop.main.js:653:60089) at zFe.h (vscode-file://vscode-app/usr/share/kiro/resources/app/out/vs/workbench/workbench.desktop.main.js:533:37342) at vscode-file://vscode-app/usr/share/kiro/resources/app/out/vs/workbench/workbench.desktop.main.js:533:36734 at Array.map () at Object.factory (vscode-file://vscode-app/usr/share/kiro/resources/app/out/vs/workbench/workbench.desktop.main.js:533:36722) at vw.j (vscode-file://vscode-app/usr/share/kiro/resources/app/out/vs/workbench/workbench.desktop.main.js:31:74383) at vw.k (vscode-file://vscode-app/usr/share/kiro/resources/app/out/vs/workbench/workbench.desktop.main.js:31:74516) at vscode-file://vscode-app/usr/share/kiro/resources/app/out/vs/workbench/workbench.desktop.main.js:31:74425 workbench.desktop.main.js:11124 An iframe which has both allow-scripts and allow-same-origin for its sandbox attribute can escape its sandboxing. mountTo @ workbench.desktop.main.js:11124 vscode-file://vscode-app/usr/share/kiro/resources/app/out/vs/workbench/services/extensions/worker/webWorkerExtensionHostIframe.esm.html?&vscodeWebWorkerExtHostId=bcc46c11-7bf3-48a4-a1a4-667d78c4e623:1 An iframe which has both allow-scripts and allow-same-origin for its sandbox attribute can escape its sandboxing. workbench.desktop.main.js:35 INFO Started local extension host with pid 7643. workbench.desktop.main.js:35 INFO Extension host (LocalProcess pid: 7643) is unresponsive. workbench.desktop.main.js:10959 Extension host (LocalProcess pid: 7643) terminated unexpectedly. Code: 132, Signal: unknown xb @ workbench.desktop.main.js:10959 workbench.desktop.main.js:35 ERR Extension host (LocalProcess pid: 7643) terminated unexpectedly. The following extensions were running: kiro.kiroAgent, vscode.git-base, vscode.emmet workbench.desktop.main.js:35 INFO Automatically restarting the extension host. workbench.desktop.main.js:35 ERR Canceled: Canceled at Dy (vscode-file://vscode-app/usr/share/kiro/resources/app/out/vs/workbench/workbench.desktop.main.js:7:1004) at vscode-file://vscode-app/usr/share/kiro/resources/app/out/vs/workbench/workbench.desktop.main.js:10952:38456 at Array.forEach () at iht.dispose (vscode-file://vscode-app/usr/share/kiro/resources/app/out/vs/workbench/workbench.desktop.main.js:10952:38396) at WCe.dispose (vscode-file://vscode-app/usr/share/kiro/resources/app/out/vs/workbench/workbench.desktop.main.js:10952:50088) at XMs.dispose (vscode-file://vscode-app/usr/share/kiro/resources/app/out/vs/workbench/workbench.desktop.main.js:10959:7303) at JMs.stopAllInReverse (vscode-file://vscode-app/usr/share/kiro/resources/app/out/vs/workbench/workbench.desktop.main.js:10959:6605) at async Kot.rb (vscode-file://vscode-app/usr/share/kiro/resources/app/out/vs/workbench/workbench.desktop.main.js:10958:15546) vscode-file://vscode-app/usr/share/kiro/resources/app/out/vs/workbench/services/extensions/worker/webWorkerExtensionHostIframe.esm.html?&vscodeWebWorkerExtHostId=2651a137-5c83-45f1-8238-07fd997a635e:1 An iframe which has both allow-scripts and allow-same-origin for its sandbox attribute can escape its sandboxing. workbench.desktop.main.js:35 INFO Started local extension host with pid 7696. workbench.desktop.main.js:10959 Extension host (LocalProcess pid: 7696) terminated unexpectedly. Code: 132, Signal: unknown xb @ workbench.desktop.main.js:10959 workbench.desktop.main.js:35 ERR Extension host (LocalProcess pid: 7696) terminated unexpectedly. The following extensions were running: kiro.kiroAgent, vscode.git-base, vscode.emmet workbench.desktop.main.js:10926 Extension host terminated unexpectedly 3 times within the last 5 minutes. c @ workbench.desktop.main.js:10926 workbench.desktop.main.js:35 ERR Canceled: Canceled at Dy (vscode-file://vscode-app/usr/share/kiro/resources/app/out/vs/workbench/workbench.desktop.main.js:7:1004) at vscode-file://vscode-app/usr/share/kiro/resources/app/out/vs/workbench/workbench.desktop.main.js:10952:38456 at Array.forEach () at iht.dispose (vscode-file://vscode-app/usr/share/kiro/resources/app/out/vs/workbench/workbench.desktop.main.js:10952:38396) at WCe.dispose (vscode-file://vscode-app/usr/share/kiro/resources/app/out/vs/workbench/workbench.desktop.main.js:10952:50088) at XMs.dispose (vscode-file://vscode-app/usr/share/kiro/resources/app/out/vs/workbench/workbench.desktop.main.js:10959:7303) at JMs.stopAllInReverse (vscode-file://vscode-app/usr/share/kiro/resources/app/out/vs/workbench/workbench.desktop.main.js:10959:6605) at async Kot.rb (vscode-file://vscode-app/usr/share/kiro/resources/app/out/vs/workbench/workbench.desktop.main.js:10958:15546) ```

Re: Kiro: A new agentic IDE

#468

Post by a5c11 » Wed, Jul 16, 2025, 8:50 AM UTC

sirsinsalot wrote: post #385

a5c11 wrote: post #365

Earlier quoted context omitted.

And we re-invent the wheel basically. You have to use very specific prompts to make the computer do what you want, so why not just, you know... program it? It's not that hard. Natural language is trying to be a new programming language, one of many, but it's the least precise one imho.

I agree with this. There's so much snake oil at the moment. Coding isn't the hard part of software development and we already have unambiguous language for describing computation. Human language is a bad choice for it, and we already find that when writing specs for other humans. Adding more humaness to the loop isn't a good thing IMHO. At best an LLM is a new UI model for data. The push to get them writing code is b…

> Coding isn't the hard part of software development

That's actually a relief, when after hours and days of attending meetings and writing documentations, I can eventually sit in front of my IDE and let my technical brain enjoy being pragmatic.

Re: Kiro: A new agentic IDE

#469

Post by a5c11 » Wed, Jul 16, 2025, 9:20 AM UTC

stillpointlab wrote: post #382

a5c11 wrote: post #365

Earlier quoted context omitted.

And we re-invent the wheel basically. You have to use very specific prompts to make the computer do what you want, so why not just, you know... program it? It's not that hard. Natural language is trying to be a new programming language, one of many, but it's the least precise one imho.

> Natural language is trying to be a new programming language, one of many, but it's the least precise one imho. I disagree that natural language is trying to be a programming language. I disagree that being less precise is a flaw. Consider: - https://www.ietf.org/rfc/rfc793.txt - https://datatracker.ietf.org/doc/html/rfc2616 I think we can agree these are both documents written in natural language. They underpin the…

> I disagree that being less precise is a flaw.

> Biological evolution shows us how far you can get with "good enough".

That are valid points when speaking about human-human interactions where we can allow ourselves for much more freedom in forming thoughts. But still, written text never will be as expressive as face to face communication when you can hear, see and feel emotions. So even for humans, a raw text is not enough. But it's good enough for biological brains.

When speaking about human-computer interactions, you are just being ignorant. Programming is engineering, and engineering is not biology. Biology allows itself for freedom and randomness, in engineering we rather avoid that kind of stuff unless it's a part of the job. Would you use a "good enough" banking system? Would you use a car with "good enough" safety features? Would you happily cross a bridge which is just "good enough"?

We invented computers to replace humans in critical jobs requiring fast and precise actions. Natural language is not sufficient to give precise instructions concisely because it was never meant to. Sure you can hammer nails with pliers, but... we have hammers.

> In such a world, I would prefer to be an expert in writing specs rather than to be an expert in implementing them in a particular programming language.

Words of a man who didn't choose his career path properly.

Re: Kiro: A new agentic IDE

#470

Post by theshrike79 » Wed, Jul 16, 2025, 10:16 AM UTC

touristtam wrote: post #370

theshrike79 wrote: post #142

Earlier quoted context omitted.

I just have a “neutral” guidance markdown setup written in a repo. Then I add it as a git submodule to my projects and tell whatever agents to look at @llm-shared/ and update its own rule file(s) accordingly

I don't add them as submodule but just symlink and ignore them globally so they never find their way into codebase; I have colleagues that frown upon using LLMs, and. I am not going to start a war over their preferences.

This is just for my personal projects. I noticed I was copy-pasting the same crap to claude/gemini/cursor/windsurf/whatever and figured out a git submodule would be the easiest way to have the latest set of rules in every project

That way I can just add new stuff to llm-shared/, commit, push and other projects will get the same things. It also forces me to keep it generic so it fits every project.

Then I just tell whatever LLM to look into @llm-shared/ for instructions and refer to files there when needed instead of having them in the "main" context file.