--- title: OpenAI reportedly planning Managed Agents announcement... description: OpenAI is rumored to unveil a Managed Agents feature at its DevDay event on September 29, based on leaked details from a social media account. The feature... canonical: https://daily.dev/posts/openai-reportedly-planning-managed-agents-announcement-at-devday-2026-idgeupswk twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: OpenAI reportedly planning Managed Agents announcement at DevDay 2026 | daily.dev og:description: OpenAI is rumored to unveil a Managed Agents feature at its DevDay event on September 29, based on leaked details from a social media account. The feature... og:url: https://daily.dev/posts/openai-reportedly-planning-managed-agents-announcement-at-devday-2026-idgeupswk og:image: https://api.daily.dev/og/posts/iDGEuPSwK.png og:image:alt: OpenAI reportedly planning Managed Agents announcement at DevDay 2026 og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # OpenAI reportedly planning Managed Agents announcement at DevDay 2026 **[Collections](https://daily.dev/sources/collections)** · 2 min read · 0 upvotes · 0 comments ## Summary OpenAI is rumored to unveil a Managed Agents feature at its DevDay event on September 29, based on leaked details from a social media account. The feature would reportedly let developers create Agents, Environments, and Agent Sessions directly through the OpenAI Platform, alongside a Codex Plugin for building and deploying agents with minimal manual setup. Hosting could be flexible, either on OpenAI's platform or self-hosted. A developer hinted at upcoming related work, but OpenAI has not confirmed anything officially. ## Content OpenAI has launched an Agents API in public beta, and is planning a broader Managed Agents rollout at DevDay 2026 (September 29). ## The Agents API, available now The Codex harness is now an API. You give it a task, a model, tools, and a sandbox, and it handles the agent loop itself. OpenAI manages orchestration, long-running sessions, and context - you just define what the agent actually does. It's a meaningful reduction in boilerplate. Building a custom agent loop from scratch used to mean wiring together a lot of plumbing yourself; this offloads most of that. ## Managed Agents, coming at DevDay The bigger announcement is expected September 29. According to early details, Managed Agents will let users create agents, environments, and agent sessions directly through the OpenAI Platform - no custom infrastructure required. The Codex plugin will handle building, configuring, and deploying agents, so you won't need to write the setup yourself. Agents can run hosted on OpenAI's platform or self-hosted. Some of the example use cases OpenAI has floated: - **Research agent** - searches the web and connected data sources, produces structured research - **Customer support agent** - resolves support requests, retrieves account info, escalates when needed - **DevOps assistant** - monitors deployments, investigates incidents, helps troubleshoot - **Meeting assistant** - transcribes meetings, captures action items, generates summaries - **Analytics agent** - queries data sources, generates reports, explains trends in plain language The pattern here is agents that connect to existing tools and data rather than operating in isolation - which is where most of the practical value tends to be anyway. More details expected at DevDay on September 29. ## Questions this post answers ### What is OpenAI's Managed Agents feature that's rumored for DevDay 2026? Managed Agents is a reported OpenAI Platform feature letting users create agents, environments, and agent sessions without writing infrastructure code. A Codex plugin would handle build, configure, and deploy, with agents hosted on OpenAI's platform or self-hosted. Rumored use cases include research agents, customer support agents, DevOps assistants, meeting assistants, and analytics agents. It's expected to be announced at DevDay on September 29th, though details come from testing sources rather than an official announcement. _daily.dev keeps developers evaluating agent platforms ahead of announcements like this one._ ## Community take How the wider developer community reacted, aggregated from 1 discussion and 142 comments across x (as of 2026-09-11). **TL;DR:** Reaction is mostly curious rather than celebratory: developers ask pointed technical questions about session durability, auth/credential persistence, and observability of failed runs, while a vocal minority pushes an unrelated demand for 4o and one user vents about an unrelated billing/support issue. **Sentiment:** 30% positive · 45% mixed · 25% skeptical **The case for** - Managed orchestration and long-running session handling are seen as solving real, tedious pain points teams keep reinventing themselves. - The split between OpenAI managing the agent loop and developers bringing their own sandbox is viewed as a sensible division of responsibility. - Flexibility to use different/local sandboxes rather than being locked into one is appreciated. **The pushback** - Skepticism that this is just another abstraction/monetization layer on top of the same underlying model rather than a real capability improvement. - Concern about whether failed or crashed runs leave an inspectable, replayable trail rather than being a black box. - Doubts about whether long-running sessions truly persist credentials/auth and hold up on messy real tasks versus a curated launch demo. - Comparisons to Claude's managed agents suggest some see this as a catch-up move rather than a novel offering. **By community** - x (mixed): Technical users probe durability, auth persistence, and debuggability with cautious interest, while some dismiss it as repackaged infrastructure and others hijack the thread with unrelated 4o demands and a billing complaint. **Hottest debate:** Whether the managed orchestration is a genuinely valuable reliability layer or just another paid abstraction on top of the same model with the real work (state, permissions, recovery) still unproven. **Open questions** - Does a failed or crashed run leave a replayable trail for debugging, or is it a black box? - Do tool credentials/auth persist across a long-running session, or is re-authentication required mid-run? - If the harness dies between tool calls, does it resume from a checkpoint or replay the call? - How does context/session state handle underlying repo or dependency changes during a long-running run? - How is it meaningfully different from manually orchestrating local Codex/Claude sessions with existing tools? **Highlights** > @OpenAIDevs i care less about the launch video than whether a failed run leaves a replayable trail. that is the line between a demo and something i'd trust overnight. > — [aficionado\_ai on x · 1 comments](https://x.com/aficionado_ai/status/2098158370142196218) > @OpenAIDevs Managed sessions are the right trade until one dies mid-run. If the harness dies between two tool calls, does it resume from the checkpoint or replay the call? That answer decides whether a payment or email step can live in there at all. What does the beta guarantee? > — [jayzhoupro on x · 1 points](https://x.com/jayzhoupro/status/2098156101921649009) > @AzianMike @OpenAIDevs Alright, I'll put it on a messy real session. If it holds for an hour without me babysitting, I'll take it more seriously. > — [MentorSurge on x](https://x.com/MentorSurge/status/2098163290287325557) > @OpenAIDevs Orchestration is the right thing to take off people's plates. Running my own agents daily, almost none of my failures are the model. They're handoffs, permissions, and a job that quietly never started. Managed sessions help only if I can see into them. > — [LoganWinns on x](https://x.com/LoganWinns/status/2098156856623730931) > @OpenAIDevs every new "agents api" is just another abstraction layer on top of the same llm that u now gotta pay extra for. the product doesnt make the model better it just monetizes the complexity the company itself created around "agents" in the first place > — [AndAIyou on x](https://x.com/AndAIyou/status/2098156672472449442) **Source threads** - [x](https://x.com/OpenAIDevs/status/2098130570048045453) · 0 points · 142 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#openai](https://daily.dev/tags/openai), [#openai-codex](https://daily.dev/tags/openai-codex) [View this post on daily.dev](https://daily.dev/posts/openai-reportedly-planning-managed-agents-announcement-at-devday-2026-idgeupswk) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"OpenAI reportedly planning Managed Agents announcement at DevDay 2026","url":"https://daily.dev/posts/openai-reportedly-planning-managed-agents-announcement-at-devday-2026-idgeupswk","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/openai-reportedly-planning-managed-agents-announcement-at-devday-2026-idgeupswk"},"datePublished":"2026-09-08T15:53:28.998Z","dateModified":"2026-09-11T07:29:40.159Z","description":"OpenAI is rumored to unveil a Managed Agents feature at its DevDay event on September 29, based on leaked details from a social media account. The feature...","isAccessibleForFree":true,"articleSection":"Collections","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Collections","logo":"https://media.daily.dev/image/upload/s--fk_6ycEi--/f_auto,q_auto/v1780996001/logos/collections?_a=BAMAMiWQ0","url":"https://daily.dev/sources/collections"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/openai-reportedly-planning-managed-agents-announcement-at-devday-2026-idgeupswk","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,openai,openai-codex","timeRequired":"PT2M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Collections","item":"https://daily.dev/sources/collections"},{"@type":"ListItem","position":3,"name":"OpenAI reportedly planning Managed Agents announcement at DevDay 2026"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/openai-reportedly-planning-managed-agents-announcement-at-devday-2026-idgeupswk#faq","mainEntity":[{"@type":"Question","name":"What is OpenAI's Managed Agents feature that's rumored for DevDay 2026?","acceptedAnswer":{"@type":"Answer","text":"Managed Agents is a reported OpenAI Platform feature letting users create agents, environments, and agent sessions without writing infrastructure code. A Codex plugin would handle build, configure, and deploy, with agents hosted on OpenAI's platform or self-hosted. Rumored use cases include research agents, customer support agents, DevOps assistants, meeting assistants, and analytics agents. It's expected to be announced at DevDay on September 29th, though details come from testing sources rather than an official announcement. daily.dev keeps developers evaluating agent platforms ahead of announcements like this one."}}]} ```