Agent Teams

Resolved 💬 9 comments Opened Feb 11, 2026 by elliotxin Closed Apr 6, 2026
💡 Likely answer: A maintainer (etraut-openai, contributor) responded on this thread — see the highlighted reply below.

What variant of Codex are you using?

CLI

What feature would you like to see?

Can add Agent Teams function to Codex like claude code did?

Additional information

_No response_

View original on GitHub ↗

9 Comments

etraut-openai contributor · 5 months ago

Can you say more about what problem you'd like to see solved? What is the use case you have in mind?

Grinsven · 5 months ago

He is talking about this here https://code.claude.com/docs/en/agent-teams

jonny5203 · 4 months ago

This may be a difficult challenge I think, as they have to implement a way for sub-agents to communicate with each other first.

pomazanbohdan · 4 months ago

Codex should not have command development algorithms; it should only provide instrumental capabilities.
There is a possibility for agents to perform tasks, which should be orchestrated by an external element.
My implementation of such a tool and examples of agent configuration settings are available in the repository https://github.com/pomazanbohdan/vida-stack.

jonny5203 · 3 months ago

Are there plans to make sub-agents communicate with each other at runtime?

are-scenic · 2 months ago

Why is it marked as completed? I haven't seen Agent Teams in Codex, only sub-agents that are unable to communicate with one another only via the team leader, which is bad for the context window.

MunMunMiao · 1 month ago

This is a good feature, it should not be marked as completed. Also, subagent and agent teams are two separate things.

EcMarius · 1 month ago

why is it marked ask complete? lmaoo

etraut-openai contributor · 1 month ago

The OP closed this issue as complete. If you'd like to suggest something similar, feel free to open your own enhancement request.