OpenAI Agents API (developers.openai.com)

260 pointsby aquir14 hours ago144 comments

bluesnowmonkey 11 hours ago

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 this lets you plug in the tools it needs to be whatever kind of agent you want. But they still get to encapsulate and continue to iterate on the really deep parts of the harness that all agents need like memory and context management.

That said, my money right now is not on the offerings from OpenAI and Anthropic because they’re stuck using their own proprietary frontier models and those aren’t actually the best choice for most agents right now. A competitor who is not an LLM lab gets their pick of the market at any given moment. Like you’d want to be using GLM 5.3 Flash right now for most things agentic.

zackify 11 hours ago

I just have a slack bot running on a VM that sees a message and invokes pi.

It would be trivial for every request to clone a full lxd container and have all the tools and repos required if I wanted to allow it to do even more.

Not sure why anyone prefers to choose locked in options

throw1234567891 11 hours ago

> Not sure why anyone prefers to choose locked in options

Convenience. And OPEX vs CAPEX something something.

notatoad 11 hours ago

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’re not a dependency of anything. And that’s as much as I’m willing to trust OpenAI or Claude.

btables 10 hours ago

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

bluesnowmonkey 10 hours ago

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?

sebmellen 7 hours ago

Truly love the website.

sebmellen 7 hours ago

Although I must say this threw me off:

> Steer clear of load-bearing tech debt as your agents evolve.

Satirical?

SpikeyCoder 7 hours ago

Interesting concept, but blue ocean as to your target customer. Would be good to see other case studies, use cases for this. Also, thank you for not another “bring your keys” product. Just abstract it away for me.

andai 5 hours ago

Interesting web design. It's rare to see a mobile website with actual personality.

(In fact, "need to support mobile" is the main reason given for the loss of personality from the web as a whole!)

danielmarkbruce 11 hours ago

There might not be a good abstraction. I've built a few harnesses for different types of workflows, and the details are so different I struggle to see a good abstraction. It's also not clear there should be - if you look at most complex software systems, it's a collection of smaller abstractions/tools/systems pulled together to achieve X.

layoric 10 hours ago

> Where does the state persist?

Spider men meme of developers pointing at each other thinking "Not it".

kmansm27 10 hours ago

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.

myzie 10 hours ago

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

ra 10 hours ago

> 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.

sroussey 8 hours ago

> All of this is specified in the ACP spec

Oh good reminder. I need to do that.

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

prompt caching is weirder than i originally thought, and so variable across providers. Retry is easy, but can you explain more on tool design?

bob1029 10 hours ago

> 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.

surgical_fire 9 hours ago

> It's not possible to fight OpenAI or Anthropic's engineering teams

And yet, I find Pi so much better to work with than Claude Code.

teruakohatu 9 hours ago

I don’t find it better than Claude Code but much better than OpenCode. So I am curious why less is more in that context.

lukebuehler 9 hours ago

I've been working on a custom managed agent (see my other top-level comment), I find it is actually a manageable undertaking. It does feel herculean, but somehow doable. I do not find their hidden reasoning tokens to be insurmountable as long as you match the behavior of codex or CC (which takes work, but, again, is doable). My managed agent harness currently matches Codex on several benchmarks like Terminal Bench.

ernsheong 8 hours ago

I built my harness in pi within herdr, I cloned (zipped and downloaded) 0xRichardH/pi-herdr-subagents and went from there, and used pi to build itself, adding gate workflow state control, provider fallbacks (I use many token plans), subagent skill injection, etc.

It is highly custom to my needs and wants, and I think every developer needs to do this. I only talk to my planner which plans, and it subs out to designer, oracle, coders, testers, and reviewers, etc. It is thus highly optimized for correctness. You can TDD or no TDD. You can fast track small changes. I tweak my harness dozens of times as I encounter new edge cases (esp when I switch models and encounter models not as good at following instructions).

As you can start to see, it is better to own the harness because nobody can build something custom that 100% fits your needs or development philosophy.

boredtofears 5 hours ago

I'm very interested in this but I am confused on what Pi provides you if you are building the harness? What does Pi get you that writing from scratch doesn't?

Any good starting points or tutorials you recommend?

kadoban 5 hours ago

Pi is just a nice base and it has defined extension protocols and such. You might as well start there, it's just easier and going from nothing to working to adding whatever functionality is like 2 minutes.

tokioyoyo 5 hours ago

Correct me if I'm wrong, but the harness will always be dependent on the underlying model, and useless without it. All custom harnesses are being built, could be obsolete in the next big-generation-jump of the models.

I might be absolutely wrong, but "harnesses" / cc-derivatives became "good enough" only maybe a year ago max. Before that, people were pushing for gigantic folder structures with custom documents and "pretend you're X" stuff.

My point is, depended on what you're trying to achieve, testing out current-gen harnesses, and nudging your workflows towards them might be better RoI, rather than chasing something that might be throwaway code a quarter later.

Obviously, this really depends on whether you believe model development will speed up or slow down in the upcoming future.

athrowaway3z 3 hours ago

You are wrong. I honestly am having trouble understanding how you think these things work, and what you believe a harness is in the first place.

There is the standard API that things like openRouter exposes, thats supported by every provider, and all it is, is manipulating a large blob of memory by adding your own words or asking the GPU to append new words.

Everything else around it is window dressing. All providers accept that API, (only Anthropic has blocked access on their consumer subscription tier).

Its how businesses write their 'bots'. Nobody - except the people trying to sell you "magic" - is incentivized to remove that kind of access.

I can switch out openai/anthropic/deepseek/openrouter/kimi/selfhosted at the drop of a hat. Its a big reason you'll see a comment on HN talk about "There is no moat".

Calling them cc-derivatives is wrong. I've seen many features land in other harnesses long before they came to Claude.

The only thing Claude seems to be "cheating" with is that:

- They provide Windows users a unix VM hosted on their servers - I dont want or need that

- They're better 'trained' at doing compaction / providing the illusion of continuity

- They might do automatic model-switching (not sure if they do) - not something i need.

Sure, if you're in the market for magic then dont put time in having your own harness and just accept the lock-in. Since I'm using them so much i think its worth the investment.

tokioyoyo an hour ago

Sorry, I didn’t mean to imply that what you’re doing is wrong, although re-reading my own comment sounds like so.

The capabilities of a model unlocks certain harness behaviour, and in its terms might be beneficial to automate more of your x, y, z.

I guess computer use would be an example I was thinking about. Certain models are not as good as some current models (Astra/Fable) in understanding through screenshots, or going through some hoops in some environments. As models evolve, they unlock new capabilities, that you either have to keep implementing in your harness, or using an existing one. I’m pro-using existing just because it doesn’t make sense for my org to support another dev tool internally, when there is heavy better development happening by people who focus on that.

The reason why i said cc-derivative, as far as I can see, cc was the one that convinced people “it might be a good idea to dev this way”. Sure you had some lesser known harnesses around, but a year+ ago, nobody really cared.

I don’t think, at least as of now, anything is really much of a lock in. We switch out between cc/codex/cursor and it takes trivial amount of time to set stuff up, depended on how your dev loop goes.

Again, it really depends on one’s conviction of “how fast things will develop from now on”. I personally think stuff will keep changing very fast. In a year what we think of harnesses will be different. Investing in custom tooling might be bad, as that is basically a lock-in. But again, I don’t know the future, but that’s my bet. Hovering around the edges and using what others battle test is an easy way out right now.

Also in some larger orgs, there is more friction in model choices. So you slowly start losing the benefits of model-swapping. Obviously different for personal projects.

chickensong an hour ago

A lot of what a custom harness does isn't necessarily interacting with a model, it's the framework around it. Part of harness engineering is figuring out what can be done deterministically to avoid calling an LLM. A generational jump doesn't obsolete those areas, it just means you get the right answer (maybe) faster and easier when you do call the model.

There's a difference between their harness and your harness. The latter can be tuned to your preferences, while the former cannot. A custom harness can do everything that a packaged harness cannot. Good luck getting Claude Code to coordinate with multiple model providers or deeply integrate with your environment.

The point you're making is to be a consumer, which admittedly, is probably best for most people, but it's not going to satisfy the hacker. Normies aren't building custom harnesses, so your argument is DOA for the target demographic.

Also, vendor lock-in. No thanks.

_davide_ an hour ago

I switched between several local and remote providers and models and over different API (anthropic/openai) and it worked fine, just some minor issues but they were fixed within an hour.

And the system prompt worked great regardless, so i don't think your main point holds, especially as models improves; it isn't throwaway code, but for sure it's evolving constantly, as my own workflow keeps changing.

> My point is, depended on what you're trying to achieve, testing out current-gen harnesses, and nudging your workflows towards them might be better RoI, rather than chasing something that might be throwaway code a quarter later.

Fair point, depends if it's an hobby or you are a developer full time, in the latter case i think it's definitively worth it.

dsrtslnd23 2 hours ago

I also built a custom harness tailored to my needs using pi.dev underneath. From time to time I use the 'official' harnesses of openai/anthropic but can't confirm that they are much better adapted to that harness.

durdn an hour ago

I did a similar thing, took those sub agents primitives and ran with it: https://github.com/durdn/herdr-interactive-subagents I do still use more than one harness though.

_davide_ an hour ago

100% every professional developer at some point should build its own harness as daily driver

mingqiz 7 hours ago

Yet i find claude code worse than opencode.

stymaar 4 hours ago

I don't think anyone who's tried something else can like claude code. The only reason to use it is the subsidized plan and nothing else.

z2 5 hours ago

After being burned by the rug-pull of OpenAI retiring the Assistants API in favor of Responses last year, I swore off using heavily stateful APIs for language model access. I could be totally wrong, but at this point I'm more willing to use a proprietary harness headless than to abstract it into an API.

reissbaker 3 hours ago

I feel like you could use an open-source harness like Pi and get 100+% of what these closed APIs offer without getting locked to OpenAI. What do you think is missing from them?

bob1029 an hour ago

Lack of risk to the business. If it was just me and my tinker toys, the open path makes a lot of sense.

I am in the business of provisioning custom AI robots for paying customers. I need to be able to provide certain assurances and offer operational simplicity or the whole thing falls apart. These systems need to survive in their environments. Accounting and compliance teams feel a lot more comfortable with the landscape around the frontier model companies.

If I went to my favorite client on Monday and tried to sell them what HN seems to think is the most ideologically pure AI solution, I would probably be fired as a vendor.

_davide_ an hour ago

> > building your own harness is a huge undertaking, a deep rabbit hole. > I eventually gave up on this task.

It's not trivial, but cmon, i did during weekends from my phone and FOR ME it's so much better than the codex or claude, it has every i need and want :D

I'm using my own harness for work and hobby, has github integration, review mode, interactive voice mode, overlayed worktree, browser integration, mcp and much more.

Using claude and codex feels like picking up a club, in-line with the caveman skill...

wiei 9 hours ago

Agents are the wrong paradigm entirely and have limited places where they actually belong.

Going off and searching the web isn't really it.

You need to create 'new worlds' where they can operate best - and even then constrain what it does.

skinfaxi 9 hours ago

I think things like onecli are the direction we will take. The secrets and state will be proxied api calls.

jgraettinger1 8 hours ago

The best answer I’ve come to thus far is the model we (estuary.dev) are building out now: offering mcp.estuary.dev with tools for creating a sandbox with our CLI pre-installed, a tool for requesting that a tightly scoped access token be injected into a named sandbox file (this is the approval gate), and a tool for executing arbitrary commands in the sandbox (presumably our flowctl CLI, but let the model rip).

The intent is that anybody can drive it from Claude/ChatGPT/Pi on their phone after MCP sign-in (oauth), the model has full computer use capability, but we can also leverage it to build guided agent workflows in our own dashboard.

dools 7 hours ago

> LLMs are a great foundation but building your own harness is a huge undertaking, a deep rabbit hole

I’ve been doing this for the past few months. I started with a server where I ran pi in tmux and then used that to build an LLM gateway and agent session manager, then built deterministic workflows using bash scripts and a skill/script distribution system. The app works on desktop, mobile and web and it works great. Non technical colleagues are using it to build and ship real software and it’s cheap AF even using API pricing because it works well with Luna or deepseek.

w-ll 7 hours ago

This is the "i made a voice controlled agent" thread all over again. lol, I too have made a stable of harnesses and tools to run them and have different levels of them monitoring each other and different spends to code/review/triage.

andai 5 hours ago

I also use Luna and DeepSeek in a custom harness. (Mine is very minimal.) GLM also works great.

I had issues with some other models but it seems to do with the system prompt and tool calling format. Some models seem to only work well with some harnesses.

dools 4 hours ago

Ha yeah GLM and Kimi seem to always biff the tool calls. I recently added in a raw stream log switch to diagnose but since DS and Luna are so good and cheap I haven’t been that motivated to debug it …

arcanemachiner 6 hours ago

> you’d want to be using GLM 5.3 Flash right now for most things agentic

That was yesterday. I think the crown currently belongs to DeepSeek Flash v4.1 for the next few days or weeks.

hadlock 6 hours ago

I can't wait for next week

selvan 6 hours ago

Libraries such as agent development kit (https://adk.dev/) provides abstraction over multiple LLM vendors, long-term memory (persistance + compaction) and allow us to manage subagents & their lifecycles. Vendor neutral memory & context management is a challenge as default long-term memory uses vertext AI (gemini) in ADK.

vikramkr 5 hours ago

IMO building a harness is not wildly difficult (customize pi?) but the offerings from openai and anthropic are wildly subsidized in the subscriptions so they win by default if you want frontier capabilities. Glm 5.3 flash is great but it's not cheaper than a codex or Claude code 200 dollar sub and it does not have astra or fable level capabilities.

andai 5 hours ago

Try 50 lines!

https://minimal-agent.com/

I made my own harness based on this, which I jerry rigged to a Codex sub.

asim 3 hours ago

Is GLM 5.3 Flash that good? I'm using it through atlascloud for my current project and testing performance against opus and gemini models. I think I'm mostly concerned about speed because they are mostly doing tool calls.

Also yes to an open runtime.

sarjann 41 minutes ago

Been using bedrock agent core and seems to work fine for me. Although there might be a better abstraction.

6thbit 10 hours ago

Buried in there, note you can opt to self-host your sandbox

https://developers.openai.com/api/docs/guides/agents-api/env...

That makes this much more enticing, and potentially eases transition between providers.

dakolli 8 hours ago

Then why tf do i need their api

Havoc 8 hours ago

For the lock in

agentdev001 7 hours ago

Native integration with their SDK.

cube00 7 hours ago

Going to be GitHub self hosted runners all over again, you pay for the API and also pay for your own self hosting.

dannyw 7 hours ago

Some people/companies/whatever might like the convenience and scalability of managed solutions, especially if you're say, just building something simple like a Slack bot with your custom workplace tools/data.

Yes, the lock-in is real and only good for OpenAI, but there's absolutely demand for managed services where you defer the responsibility of security patching; scaling; uptime, etc to a third party provider. Just like why people use AWS/GCP/etc over bare metal in a colo.

andrewguenther 6 hours ago

The self-hosted environment is just the backend for shell calls the agent wants to make. The inference bits, thread persistence, and (optionally) mcp/tool calls happen from the API.

andrewchambers 12 hours ago

I've recently had great success running codex in a regular qemu VM and using codex remote control to talk to it from my phone.

Honestly works extremely well as a personal assistant.

I can see why turning it into an API makes sense, just be aware you might not need to lock yourself in if you can setup your own VMs.

krashidov 12 hours ago

Do you have 1 long running session?

andrewchambers 11 hours ago

Codex remote control serve can run continuously.

Sometimes start a new chat in the phone app, sometimes just add to the main one. Both seem to work ok.

If I want the agent to wait for something I need to start a new chat in the iphone app.

windexh8er 11 hours ago

Considering the harness needs to be running how else would this work?

Pretty easy these days with old school tools like tmux but more modern tooling like herdr [0] is really the path you'd want to take.

[0] https://herdr.dev/

andrewchambers 11 hours ago

codex itself has a remote control mode that runs continuously. I wrote a systemd service to start it boot and interact with it via my phone.

windexh8er 11 hours ago

But Codex doesn't survive a reboot by default or a laptop going to sleep. Also, herdr is abstracted up a level from the agent, so you actually get more benefit by using Codex with herdr because herdr knows how to operate Codex, and other harnesses. So if you're using multiple Codex instances you can orchestrate them because each harness can talk to the others. You can still interact with Codex running in herdr via remote control (ideally you'd target your "orchestration" Codex instance). It just gives you way more power.

krashidov 11 hours ago

> Considering the harness needs to be running how else would this work?

you can just make new sessions for each new task?

sejje 9 hours ago

i tend to do this, or at least every so often.

i just give it a config (agents.md etc) to where it knows what's going on, or can figure it out

blfr 11 hours ago

Yes, I do the same with Claude Code. Create an instance on the server for a project and then can create sessions from any device, close my laptop while claude code keeps working, etc. without losing the convenience of dedicated apps.

kyxsc 11 hours ago

Yep I run `claude remote-control` as daemons (systemd/launchctl) on whatever paths/repos I wanna be able to create a session from on-to-go.

Works really well and is a great use case for work laptops. Same shell, same memories, same sessions

bmurphy1976 9 hours ago

I've been running Hermes inside a remote docker container connected to Slack bound to a Codex account. It's actually pretty great, I prefer this approach for a lot of things. Because it's in a Docker container I have 100% control over the configuration. It may do some crazy stuff, but I know it's not going to start exfiltrating my AWS SSO tokens or SSH keys from my laptop.

lukebuehler 8 hours ago

The key here is that they are _not_ just turning "running codex on a VM" into an API. Their harness is running outside a VM, interacting with a VM when needed. See the diagram in their post. This allows them to scale the agent runs independently from the VMs. That's why they call it "managed Codex harness", it's a different version than what you run.

Havoc 8 hours ago

May as well go for Hermes at that stage

pavo-etc 7 hours ago

I've done something similar by running pi within an xmpp wrapper on my server, so I can talk to it from any phone or computer. Works super well.

mrieck 7 hours ago

I do the opposite. I have a Slack bot that communicates with an app on my Mac mini that dispatches agents for tasks. It knows all my projects and also has a scheduler that uses the Herdr API. That way I can have things running on my Claude/Codex subs at home 24/7.

Setting up all my code, environment, context, etc in the cloud on VMs seemed like a lot so instead I send back tasks to my Mac mini(s) that are running at home.

monneyboi 12 hours ago

Instead of this push for more vendor lock-in, give us the reasoning tokens we pay for. Thanks.

_pdp_ 10 hours ago

There are vendor neutral solutions too https://github.com/chatbotkit/platform

brap 8 hours ago

I think the line between regular LLM "endpoints" and agents/harnesses is going to become more and more blurry until it's a meaningless distinction.

When you're using ChatGPT/Claude/Gemini etc. you're basically already interacting with some backend harness with tools etc., not a raw LLM. Just give it a computer and be done with it.

I already find myself using Claude Code / Antigravity (via web) instead of Claude / Gemini, even for tasks unrelated to coding. Why use a limited version?

dabbz 5 hours ago

This bothers me so much with the existing offerings. I start with the chat interface then as soon as I want to get technical/run scripts/automation, I have to copy the context into a fresh code session. So cumbersome.

zmmmmm 5 hours ago

This idea of remotely hosting the agent harness is honestly backwards to what I need.

In so many cases, all the friction is about how to provision access to local data so the agent can work. So you started with the problem of how do I integrate an agent that is running locally with data that is hosted locally, and you have to deal with a bunch of security, data sensitivity and management issues around that. Now you moved the agent to a remote host - pretty much all your problems are worse: now I have a remote agent reaching into my infrastructure to deal with.

I'd much rather the inverse of this: let me run the agent local but provide secure remote hosted sandboxes. That actually solves a real problem because the sandbox running locally means breaking out of it directly intersects your local infra, whereas if it runs in a managed hosted environment I can leave the provisioning and management of that to someone else.

tokioyoyo 5 hours ago

The end goal is not you watching what the agent is doing, verifying, then accepting its changes. In the ideal scenario of automation, the agent does it on your request, doesn't matter wherever you are.

Kind of slack-button-click-to-fix-something workflow.

karakanb an hour ago

I launched Epho a few weeks ago as an API like this but for all harnesses: https://epho.io

I built it primarily for ourselves: we are building an AI data engineer, and we need a way to run many of them in parallel securely. An API for this seemed like the most obvious path forward. It makes it trivial to bring agentic capabilities into any product surface without having to deal with sandboxes, reliability issues, compatibility problems, and more.

I think it also makes sense from OpenAI's perspective to do this, but also we did find ourselves needing to change models and harnesses quite a bit, which is why I think this needs to be a layer of its own above the labs. It also needs to be a layer above the sandboxes, since many of them are quite brittle.

Overall, I expect a lot of the agent implementations to move in this direction. I think this is a lot saner for engineers to implement and maintain, and it makes it trivial to build agentic stuff into products.

MatekCopatek an hour ago

I've commented about this before, I think many LLM based apps nowadays are at risk of being replaced by a product straight from the labs once they prove to be successful.

We've seen this pattern with Apple making their own version of an app that was previously popular on the app store.

The labs are in a perfect position to do this - they have a bunch of data on what's being used and they have direct access to their own models/compute. If an external service is popular, it's relatively trivial for them to estimate how much additional profit they're leaving on the table.

If the usecase isn't far from their core business (and things like this absolutely aren't), with their size, why wouldn't they eat other people's lunches?

druskacik 3 hours ago

I actually have a good use case for this. For my project, I run a lot of Codex sessions in parallel (via Codex SDK[0]), because they are solving self-contained tasks (building crawlers for websites) and in theory I could scale it to hundreds or thousands of parallel sessions. But my VPS can handle maybe 10 parallel sessions max.

Btw, the crawlers are for classical music websites, the project is https://classicalbot.com/ .

[0] https://learn.chatgpt.com/docs/codex-sdk

yangshi07 3 hours ago

I believe is not a good idea for the model providers provides a Agent Infrastructure or hosting service.

This area should be open source and supported by the cloud providers. Because I don't really want to be locked to a model provider when I am building my agents.

Actually this is happening, I found couples:

- https://flueframework.com from Astra - https://eve.dev from Vercel - https://fastagent.sh looks more independent, cloud neutral

There should be more and more options, the OpenAI Agent API may be another GPTs

jval43 26 minutes ago

It's entirely possible future models will refuse to answer if they notice you're using an external harness.

Instead they'll point you to their respective vendor APIs for the specific use cases.

We're talking about trillions in value to be captured, they'll try everything.

socketcluster 2 hours ago

Though I'm not surprised by this offering, I feel like I need some time to absorb it. It feels like the stepping stone to the next big thing.

It's going to destroy a lot of startups which were monetizing this exact idea. But clearly it's a low-hanging fruit so it makes sense that OpenAI would do it.

baalimago 4 hours ago

I've had great success with the OpenAI agents SDK [0]. This way I've been able to build the sandbox + slack + knowledge-bank integrations independently and be very strict with what I expose to OpenAI.

Looking at the Agents API, it seems like it offers similar capabilities, but reduces the need for hosting? So I get it from a business standpoint, but hosting a python service is very easy now a days, so I don't see the point as a consumer.

[0]: https://openai.github.io/openai-agents-python/

dakolli 3 hours ago

Why not just build this yourself, you literally have AI, why wall yourself into an OpenAI garden. These sandboxed environments are trivial to build.

baalimago 3 hours ago

I found that trying to keep up with their API updates and changes is more trouble than its worth, even with AI. The agents would need to reverse engineer from the OpenAI SDK source anyways, so why not cut the middleman?

If I wanted something portable for multiple providers, I would of course not use the OpenAI SDK at all. It's a conscious choice to go with OpenAI (in this design), it fits for my company at the moment.

chairhairair 12 hours ago

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

Aperocky 5 hours ago

I think in time people will realize harness is essentially a more complicated .vimrc or .zshrc;

And yes, you can install gigantic plugins in those places - e.g. Codex; but the point is everyone will have exactly what they have customized towards. The more atomic a building block is, the easier it can be adapted into any kind of configuration.

I think the pain of selling a harness is if your target market understand what a harness is, then they can build it to exactly how they'd like it without much effort. If they don't, then the harness wouldn't be very useful to them in the first place.

kingstnap 12 hours ago

This is pretty interesting in a lot of non-surface-level ways.

I can see OpenAI pushing for this as a sort of more durable moat compared to the now huge number of agentic harnesses that run on your own machine.

This might be getting the foot into some sort of bundling as well. Like unrestricted models or custom fine tuned agents inside this and not providing direct APIs to those endpoints.

That being said I don't see a lot of reasons for people to jump on this if it doesn't bundle something killer. Like to me the fact that GPT Work runs on your own machines and all the artifacts and work in progress there for you to look at is sort of the whole point. I don't just want a final artifact.

wyre 12 hours ago

>GPT Work runs on your own machines...is sort of the whole point.

Which is also why they want to remove it from your machine. Call it conspiratorial, but I keep thinking about "You'll own nothing and be happy." It seems like the industry is quickly moving in a direction where devices are turning into gateway into the cloud, and personal computing will turn into a hobby that prices out the average individual.

sejje 9 hours ago

I mean, they didn't say "you can't download the product of your work" or something.

wyre 9 hours ago

Sure, but neither did I. I summarized the quote, but OP's full quote included the the value of having the work artifacts and works-in-progress on your system to look at. If you are developing software on a VM, there will still be tools to view the artifacts remotely, but this Agents API is still a sign of local development trending away.

varenc 10 hours ago

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...

jumploops 10 hours ago

It's interesting to me that the agents comparison page[0] doesn't list codex's app-server as an option.

I've found the app-server to be the most flexible, compared to the raw Responses API or Agents SDK.

Certainly seems like everyone is still figuring out the right interface here.

Also of note, since GPT-5.5 or so, Codex doesn't even use the Responses API as intended, but instead a "lite" version where they manage the context more manually (like sending the full transcript or using a custom web.run tool instead of the provided `web_search` tool).

If you follow the docs, it will lead you down a lot of well-intended functionality, but most of it is thrown away in their most successful harness.

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

lukebuehler 9 hours ago

I think this is an important direction: managed agents that control compute.

For those who are interested in a self-hosted version of the same concept, I've been working on something like this here: https://github.com/smartcomputer-ai/lightspeed

maxdo 12 hours ago

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

gavinray 12 hours ago

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

maxdo 12 hours ago

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 .

dannyw 7 hours ago

Ease of setup and accepting the lock-in; in exchange for OpenAI handling security-patching the environment, scaling containers, etc. It's an option.

pixl97 12 hours ago

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.

simonw 12 hours ago

To save yourself the hassle of running your own sandboxed VM.

pixl97 12 hours ago

Not sure I exactly trust OAI to do that right.

kakugawa 12 hours ago

I assume you'd develop via the SDK, then deploy it via the API.

542458 12 hours ago

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.

fy20 12 hours ago

Basically how Cursor Cloud Agents work?

iforgotmypasswo 12 hours ago

I just wrote my own VR harness in a weekend with Astra. It mentioned an SDK for exactly this in passing, but it was an experimental personal project so I didn’t bother to review the code.

I was doing exactly what you’re describing. I think this is a ToS violation for anything other than personal use though.

theahura 12 hours ago

do you mean like a cloud agent provider? What we're working on at noriagentic.com may be relevant -- you can fire events from slack/web/cli to kick off an agent in a box and talk to it as if it was running local

Linkd 11 hours ago

Do you guys support projects that span multiple repositories? (and can create multiple PRs across them?)

dist-epoch 11 hours ago

You can give the agent a tool (or bash script) which waits for events. Agent calls it and the tool sleeps until an event happens then returns it to the agent.

ed_mercer 5 hours ago

you mean something like step level debugging for agents?

lhk931122 9 hours ago

Six months into customizing my own Claude Code harness, I've settled on assuming Anthropic and OpenAI will just handle all of it, except turning my own flows into skills.

everlier 12 hours ago

It's actually a really great idea, but it doesn't have to go beyound existing Responses or Chat Completions APIs.

We built that in my current company and it works wonders to just script entire persistent workflows with a simple SDK.

oliver236 4 hours ago

so this is basically a massive competitor to langgraph?

podviaznikov 10 hours ago

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?

shchoholiev 11 hours ago

Pretty good abstraction. Setup your sandbox with dependencies, build plugins - agent works. Tested it with OpenAI for the last month while it was in preview

krashidov 12 hours ago

you can't use your subscription with this so it's likely the largest companies in the world that can truly use this

dist-epoch 11 hours ago

`codex -p` is the subscription equivalent. or ACP if you want to be fancy

krashidov 11 hours ago

yep. I'm saying that the managed agent API described in the article is API only.