Yet another Hacker News

36 points torutofu 1 hour ago 45 comments

pscanf 1 hour ago | parent

I have so many use cases for this. I just hope that we'll get a standard like https://www.openresponses.org/, because the idea of coupling an app to a particular vendor doesn't seem appealing at all, especially since it seems that the functionalities they offer are more or less the same. (I'm thinking about the OpenAI's Agent API and Anthropic's Agent SDK as "alternatives.)

username_my1 1 hour ago | parent

I'm starting to think that the LLMs ecosystem is going in the JS ecosystem direction, endless technologies with little to no adaption.

Literally everyday there is a new tool and the tools released last week are deprecated.

gonzalohm 1 hour ago | parent

That's the whole point with AI. It's consumerism applied to software... And it sucks

fg137 1 hour ago | parent

I see people spending so much time creating "workflow" skills that have no benchmark whatsoever to prove they are any more effective than plain one sentence prompts.

simianwords 1 hour ago | parent

This is so frustrating to me. Ever heard of the planner agent reviewer agent and the tester agent framework?

I'm not sure if that's what you mean but I know many that are making their own flow like this and think that this brings in a higher level of performance..

andyfilms1 47 minutes ago | parent

I would imagine that performance is coming from essentially dedicating 3x context windows to one task, rather than any particular inter-agent magic.

tikotus 1 hour ago | parent

This takes me back to the era of object oriented programming and UML diagrams. More time was spent framing the solution than implementing it. Is there maybe one more design pattern that could be applied? And when the time to implement came, all those diagrams were mostly in the way. But doing it was fun, since it allowed you to focus on the fun, big picture and skip the nitty gritty details that were actually hard to solve.

I feel like people are going down that slippery slope with harnesses and skills and what not. With the right prompt, and with the right model, and with a sprinkle of magic, the solution will emerge. Oh, it didn't? Let's see if there's a new model available, or if someone has come up with a new clever skill or something. Maybe then... Because actually solving annoying problems is not fun, even less so now that the code is a black box only the LLM can understand.

lifeisloving 1 hour ago | parent

It reminds me of people customizing their nvim configs all day, thinking they're being productive but not getting all that much done.

banorton 54 minutes ago | parent

Hey I never deluded myself into thinking I was being productive :)

virgil_disgr4ce 1 hour ago | parent

I don't think I'll ever understand this argument. Especially from purported "hackers."

Why is a large number of ideas, technologies, frameworks, etc. bad?

lifeisloving 58 minutes ago | parent

Its not bad, just most of them are created by corpos to sell slop to the masses. AI companies suck and you know it. Its not about good software, its about making as much money as possible before the hype train dies.

esafak 57 minutes ago | parent

'coz it's pointless if you can get the same results without them.

panzagl 7 minutes ago | parent

Hackers hate frameworks because they hide the underlying truth of a system.

QuantumNomad_ 1 hour ago | parent

Gotta justify that $160k/yr salary somehow I guess, and if the AI is writing all the code you used to write and your job is now to manage the AI, what better way to spend the days than making new AI tools and workflows and markdown files all day

wslh 39 minutes ago | parent

> endless technologies with little to no adaption.

I think the difference is that those endless technologies will probably be used by other agents without people's explicit knowledge.

maxdo 34 minutes ago | parent

why do we even care, this is a clear, lets move away from `people pushing software to git` to `agent is pushing software, agentic or not , to somehwere, db, git, or something else` human does involved in this unless there is a problem. JS or Python, is really not essential in this case, maybe it's WASM built from rust. it's not for human.

Cursor moving this direction, is a prep work where human no longer command that much , hence the usage will drop. e.g. their core product is vulnerable. Software factories, is the ultimate game over for our industry.

dangoodmanUT 23 minutes ago | parent

I attribute this to "it's so new and we don't know what the right answer is yet", but you may very well be right

thedangler 1 hour ago | parent

If you are on onstagram 99% of posts are people shilling skills where you need to subscribe to some service. To which they are an affiliate.

And a lot of the apps are the same thing.

It's going to be a race to the bottom.

scosman 1 hour ago | parent

Open AI and Anthropic already have "Agent SDK" brands. Vercel is "AI SDK". I wish folks would come up with some good names for new projects.

Raed667 1 hour ago | parent

And Google has ADK (Agent Development Kit)

simianwords 1 hour ago | parent

Honest question, why shouldn't any agent SDK's API simply be a PROMPT.md with a runtime that runs the LLM with tools; why do you need excessive abstractions over that like langchain offers?

Is it to have boundaries of some determinism?

ashishmax31 1 hour ago | parent

>runtime that runs the LLM with tools

This "runtime" is what you are building with LangChain.. A harness like claude code/codex etc is general purpose and its env is a shell + tools. But with a custom runtime (basically a loop where we ask llm what to do next), we can give it specific tools which we define in code. This can help with things like authorization since, well its custom code you own.. so the runtime gets the tools scoped to the users permissions etc.

zomtorg 37 minutes ago | parent

My 2c is that agents are not at the level where companies can easily just have unconstrained LLM with tools and let it be. Different parts of the workflow can have different models, different tools, different constraints, guardrails, etc.

The entrypoint still has to come from somewhere, and it's much more convenient to be able to explain the security and legal teams how data is handled, what is logged, how you can have control over a scenario where the agent does something unexpected.

Sure, for a personal project that could be enough, but we all know those companies target enterprise customers, and you would be surprised how little adoption there is when it comes to workflow automation due to the lack of controls.

hippycruncher22 1 hour ago | parent

Pi durable for me

holistio 1 hour ago | parent

The video is still showing @grok/agent-sdk.

Meanwhile, we know Grok Bot was really Cursor beforehand... it must be wild in there.

h0rv 1 hour ago | parent

Why would you not use an open-source harness in October 2026? I am generally curious - what is the alpha?

chrisvalleybay 1 hour ago | parent

Well, I'd love to use an open-source harness! My issue is that Opus 5.5 / Fable 5.1 has been the best model for me to work with, and it's way cheaper to use it with the subscription to Claude Code Max. I won't pay more just to use an open-source harness. I'd rather just wait it out and stay on Claude Code not having to constantly jump around / switch tools as the industry matures.

Qworg 58 minutes ago | parent

You don't have to pay more - I wouldn't switch to an open source harness on a whim, but your harness/cheaper agents can always call Claude Code headlessly.

chrisvalleybay 47 minutes ago | parent

As context: I work as a consultant and produce code on behalf of my customers. What's most important to me is that the quality of the code is as high as it can be, without me having to rerun it with multiple different models to see which agents produces the best. If Opus 5.5/Fable 5.1 (or a different model for that sake) consistently produces the best code, I will use that for all my tasks, since that lowers the cognitive burden.

The cheaper agents never really matter, because the Max subscription costs me $100 and that is less than an hour of pay. In some cases the customer even pays for the subscription.

But I do love the idea of being able to use Pi or OpenCode. I am a heavy terminal user, and used Vim/Tmux/Lazygit-types of workflows before coding agents were in the terminal, so I do love customizability and portability. Right now there is just too much ground-shift to take part in it. Better to wait it out.

julesrms 58 minutes ago | parent

You can use your claude subscription just fine in open harnesses!

I make one (https://github.com/juggler-ai/juggler) and it'll auto-detect and use your claude CLI. I use that claude plan for 90% of my work, plus a bit of GPT, I just prefer to do it inside a nicer, less locked-in environment than claude.

There's really no moat around proprietary closed harnesses, it's trivial to jump between them, but people need to be aware that it's possible!

behnamoh 55 minutes ago | parent

it goes against anthropic‘s terms of service, and people have had their Claude accounts banned for doing exactly this.

julesrms 40 minutes ago | parent

The big hoo-har about it earlier this year was because something (opencode?) was pretending to be the claude CLI and using the API that way. Anthropic made a fuss, then GPT said "we don't mind people using their own harnesses" and everyone relaxed about it, as long as the harness goes via the claude CLI and doesn't try to cheat.

aenis 54 minutes ago | parent

Locked in? I routinely switch between claude and codex, same codebases, same skills, and even shared "memories" with maybe 5 minute effort to set it up. There is no lock in whatsoever.

ramoz 1 hour ago | parent

If you tell me I should OpenCode over Claude Code in October 2026 - then you have no idea what you are talking about.

jatins 58 minutes ago | parent

say more, what do you think CC does better?

lifeisloving 55 minutes ago | parent

Im not sure how they would know, they're clearly using a singular harness.

ramoz 42 minutes ago | parent

I actively use all harnesses and maintain popular plugins across them

mkw5053 56 minutes ago | parent

OpenCode + DeepSeek V4.1 Flash Uncensored on Venice AI is truly incredible. Granted, I have it also drive an interactive claude code session in tmux and just do everything Claude Code refuses to. But, it just gets shit done. Kind of what makes Instinct so powerful, don't tell me you won't do something, just get it done.

ramoz 37 minutes ago | parent

Interesting on Instinct, I have to often tell it "just do it"

giancarlostoro 53 minutes ago | parent

Claude Code wont let me use their sub with one as far as I remember. So I'm stuck with their convoluted TUI. It does what I need, and when it doesn't I just build tools that Claude consumes. The new "Artifacts" feature has helped a bit though.

yako21000 41 minutes ago | parent

It's the one features that keeps me using claude, it's simply convenient.

sodacanner 37 minutes ago | parent

There's just not really any features in an open-source harness that blow my mind enough to move off the highly-subsidized claude code subscription. I type in instructions and it spits out code. I'm increasingly of the opinion that the more complex features being floated are productivity theater.

mikert89 1 hour ago | parent

Why would anyone use this over the Anthropic sdk

athorax 54 minutes ago | parent

You mean except for all the obvious reasons?

randomblock1 51 minutes ago | parent

Also see the existing Cursor Typescript SDK.

https://cursor.com/blog/typescript-sdk