OpenAI Launches a Dedicated Agents API
OpenAI Agents API
OpenAI has published documentation for a new Agents API, giving developers a first-class way to build and run autonomous agents. The guide covers architecture, configuration, and sessions, plus sandboxed environments — both OpenAI-hosted and self-hosted — with lifecycle and security controls. Agents can call tools including web search, functions, and MCP connections, and the docs detail multi-agent setups, observability, and tracing. A separate Agents SDK and legacy Agent Builder round out the stack.
Agents API: Overview, Quickstart, Architecture, Configuring Agents, Sessions, Environments and sandboxes, Tools and integrations, Multi-agent, Observability and usage, Tracing.
- bluesnowmonkey
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.
- andrewchambers
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.
- brap
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?
- monneyboi
Instead of this push for more vendor lock-in, give us the reasoning tokens we pay for. Thanks.
- 6thbit
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.
- 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...
- chairhairair
Perfect for when you want your data to be stolen programmatically.
- jumploops
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...