Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

OpenAI Agents API

developers.openai.com

Post reply on HN
Print view View original

61–70 of 201 posts

Re: OpenAI Agents API

#61

Post by varenc »

Their showcase examples[0] link to GitHub but the links 404. Like this one for the Slack agent: https://github.com/OpenAI-Early-Access/agents-api-python-pre...

Guessing this an early release not quite ready for the public? Interesting that there's a 'OpenAI-Early-Access' GitHub user, though of course with no public repos. Presumably when its actually public they'll move the example agent repos to another GitHub user.

[0] https://developers.openai.com/showcase/agents-api-slack-bot

edit: Maybe someone from OAI saw my comment because the links are now fixed! And they point to a public repo under the openai org: https://github.com/openai/openai-cookbook/tree/main/examples...

Re: OpenAI Agents API

#62

Post by podviaznikov »

would love if it would be possible to allow suer and signing with the open ai account and use exiting subscription.

anyone knows how to do that and implement agent api with user actual account?

Re: OpenAI Agents API

#63

Post by kmansm27 »

bluesnowmonkey wrote: post #40

I think we’re still figuring out the right abstraction for offering agents as a product. - LLMs are a great foundation but building your own harness is a huge undertaking, a deep rabbit hole. - There are harnesses available as open source libraries but that’s still coupled to an environment. Where does the state persist? Like maybe I’m a Cloudflare worker and don’t even have a file system. Agent as a service like thi…

Agree, as long as models are interchangeable, it doesn't make sense to be locked into a single lab's managed agent platform. You probably want to swap between models and own the agent state.

https://github.com/omnara-ai/omnara - this is a self hostable agent API that I'm working on. It stores the state of all agents in a postgres db you can easily query, rather than a local json file or sqlite file per agent.

Re: OpenAI Agents API

#64

Post by myzie »

bluesnowmonkey wrote: post #40

I think we’re still figuring out the right abstraction for offering agents as a product. - LLMs are a great foundation but building your own harness is a huge undertaking, a deep rabbit hole. - There are harnesses available as open source libraries but that’s still coupled to an environment. Where does the state persist? Like maybe I’m a Cloudflare worker and don’t even have a file system. Agent as a service like thi…

I built several harnesses in different products over the last two years. Fully agree with you that doing it right is a rabbit hole. Certain system properties that you almost always want in a harness used within a SaaS (for example) are non-obvious at the start and require certain architectural choices. It's easy to start down a path and then find a gap a couple days before launch.

Async tool calls, having the agent wait indefinitely for a human response, and showing a form or questions to the user via a tool call are a few common capabilities that come up that a product manager might miss at first.

This is why I've been building Nvoken. LLM agnostic, ergonomic SDKs, flexible tool call patterns, tenant and user-aware budget enforcement, etc.

I'd really appreciate any and all feedback on this! It gives you some free tokens on signup and it's super quick to try.

https://nvoken.com

Re: OpenAI Agents API

#65

Post by bob1029 »

bluesnowmonkey wrote: post #40

I think we’re still figuring out the right abstraction for offering agents as a product. - LLMs are a great foundation but building your own harness is a huge undertaking, a deep rabbit hole. - There are harnesses available as open source libraries but that’s still coupled to an environment. Where does the state persist? Like maybe I’m a Cloudflare worker and don’t even have a file system. Agent as a service like thi…

> building your own harness is a huge undertaking, a deep rabbit hole.

I eventually gave up on this task. It's not possible to fight OpenAI or Anthropic's engineering teams. Their reasoning models have all kinds of undocumented back door access to the base models that you'd never be able to replicate from the outside. Even if you had full access you would not have the engineering man hours or experience to keep up.

I think this Agents API thing is a step too far, but Chat Completion is too cold now. Something approximating Responses API seems like the happy medium. You still get most of the control with the only blackbox part being the reasoning loop / tokens. Building agents using the GPT5.6 family w/ Responses API feels pretty close to Star Trek computer shit to me. I thought I was being clever with my DIY contraption on top of chat completion, but it wasn't even close. I have embraced the reality that I will need to use opaque reasoning tokens to give my clients the experiences they are paying me to provide.

Re: OpenAI Agents API

#67

Post by ra »

myzie wrote: post #64
bluesnowmonkey wrote: post #40

I think we’re still figuring out the right abstraction for offering agents as a product. - LLMs are a great foundation but building your own harness is a huge undertaking, a deep rabbit hole. - There are harnesses available as open source libraries but that’s still coupled to an environment. Where does the state persist? Like maybe I’m a Cloudflare worker and don’t even have a file system. Agent as a service like thi…

I built several harnesses in different products over the last two years. Fully agree with you that doing it right is a rabbit hole. Certain system properties that you almost always want in a harness used within a SaaS (for example) are non-obvious at the start and require certain architectural choices. It's easy to start down a path and then find a gap a couple days before launch. Async tool calls, having the agent w…

> Async tool calls, having the agent wait indefinitely for a human response, and showing a form or questions to the user via a tool call are a few common capabilities that come up that a product manager might miss at first.

All of this is specified in the ACP spec, so if you build your agents from that - you don't end up skipping features.

Also vital is proper prompt caching, tool design and some connection retry mechanism.

Re: OpenAI Agents API

#68

Post by bluesnowmonkey »

btables wrote: post #56
notatoad wrote: post #47

Earlier quoted context omitted.

I think the abstraction is only part of the problem. The other part is that all these companies offering ai products are deeply untrustworthy, and I don’t want to let them any further into my stack than I have to. Claude code and codex are great because they are lightweight, and operate on top of the rest of my tools with little to no change needed, so they can be eliminated or migrated away from with zero cost. They…

Just letting you know, this comment inspired me to finally just say "screw it" and launch what I've been building for the past year. https://www.cadenya.com

Congrats on the launch! The readme post in the blog was helpful to understand what you’re selling. Maybe you could convey those ideas more in the homepage?

Re: OpenAI Agents API

#70

Post by myzie »

simonw wrote: post #25

The pricing on this is a bit confusing. Does each execution of an agent session create a new environment? And is that environment then billed for at least a full hour (despite prices being quoted per 20 minutes), after which it naturally expires? Is there a way to deliberately shut down an environment so you don't have to keep paying for it?

Looks like you can opt-out of having an environment via

`environment.type: "none"`

When there is an environment, my impression is it's a floor of 5 minutes at that 1 GB @ $0.03/20 min rate. So $0.0015/minute * 5 minutes = $0.0075 minimum charge per activated environment.

https://developers.openai.com/api/docs/guides/agents-api/ses... https://developers.openai.com/api/docs/pricing#built-in-tool...

Post reply on HN