OpenAI Agents API

#1

Post by aquir » Thu, Sep 10, 2026, 7:43 PM UTC

OpenAI Agents API
developers.openai.com

Re: OpenAI Agents API

#2

Post by maxdo » Thu, Sep 10, 2026, 9:08 PM UTC

Why would you choose api vs sdk . Sdk in a sandbox feels much better .

Re: OpenAI Agents API

#3

Post by 542458 » Thu, Sep 10, 2026, 9:12 PM UTC

What I want (which I don’t think exists?) is a way to trigger turns that the user can monitor in the codex application. I.e., when event X happens, my application triggers Codex to take a turn with input Y, which the user can monitor through codex. Right now the only way to get close to this is with polling or essentially rewriting a codex-like frontend.

Re: OpenAI Agents API

#4

Post by gavinray » Thu, Sep 10, 2026, 9:13 PM UTC

maxdo wrote: post #2

Why would you choose api vs sdk . Sdk in a sandbox feels much better .

https://developers.openai.com/api/docs/guides/agents#compare...

Re: OpenAI Agents API

#5

Post by chairhairair » Thu, Sep 10, 2026, 9:13 PM UTC

Perfect for when you want your data to be stolen programmatically.

Re: OpenAI Agents API

#6

Post by pixl97 » Thu, Sep 10, 2026, 9:14 PM UTC

maxdo wrote: post #2

Why would you choose api vs sdk . Sdk in a sandbox feels much better .

Because how does OpenAI earn more money then? At least to me it seems to try more vendor lock in, but I might mistaken on how easy it would be to just be another level of abstraction in an agent system.

Re: OpenAI Agents API

#7

Post by simonw » Thu, Sep 10, 2026, 9:15 PM UTC

I jumped straight to the section on configuring your sandbox's network access: https://developers.openai.com/api/docs/guides/agents-api/env...

It offers three settings:

  enabled:    Allow outbound access. This is the
    default unless you inherit a template policy.
  disabled:   Block outbound access.
  restricted: Allow only the hosts listed in allowed_domains.

Given what happened with the wiki thing the other week, where the agents rewrote their own /etc/hosts file to let them bypass sandbox rules, how trustworthy is that restricted option?

Re: OpenAI Agents API

#8

Post by maxdo » Thu, Sep 10, 2026, 9:16 PM UTC

gavinray wrote: post #4

maxdo wrote: post #2

Why would you choose api vs sdk . Sdk in a sandbox feels much better .

https://developers.openai.com/api/docs/guides/agents#compare...

I get it why do I want to use your managed session , what do you win ? Any examples ?

I’m trying to understand the use case but it seems weird middle ground in a way .

Re: OpenAI Agents API

#9

Post by fy20 » Thu, Sep 10, 2026, 9:17 PM UTC

542458 wrote: post #3

What I want (which I don’t think exists?) is a way to trigger turns that the user can monitor in the codex application. I.e., when event X happens, my application triggers Codex to take a turn with input Y, which the user can monitor through codex. Right now the only way to get close to this is with polling or essentially rewriting a codex-like frontend.

Basically how Cursor Cloud Agents work?

Re: OpenAI Agents API

#10

Post by spwa4 » Thu, Sep 10, 2026, 9:20 PM UTC

Since a week or so everything I ask codex to do, no matter how small, uses at least 1% of my weekly limits and like 5% of my 5h limit. It's getting so bad I'm thinking of just canceling my OpenAI subscription, because this has no use anymore.