openai-agents-python
https://github.com/openai/openai-agents-python
Python
A lightweight, powerful framework for multi-agent workflows
Triage Issues!
When you volunteer to triage issues, you'll receive an email each day with a link to an open issue that needs help in this project. You'll also receive instructions on how to triage issues.
Triage Docs!
Receive a documented method or class from your favorite GitHub repos in your inbox every day. If you're really pro, receive undocumented methods or classes and supercharge your commit history.
Python not yet supported3 Subscribers
Add a CodeTriage badge to openai-agents-python
Help out
- Issues
- Modal sandbox: evaluate native filesystem APIs and clarify overwrite compatibility
- Realtime: close() keeps the previous connection's item and audio state, so a reconnect on the same model truncates and retrieves stale item ids
- fix(realtime): reset per-connection state on close
- Realtime: a failing model.close() leaves every waiting event iterator blocked forever
- fix(realtime): wake event iterators when the model close fails
- Realtime: agent_end names the post-handoff agent instead of the agent whose turn ended
- fix(realtime): name the agent whose turn ended in agent_end
- fix(mcp): keep the Streamable HTTP session usable after a 5xx
- Cancelling a MCP server work task does not stop the worker
- fix(mcp): stop swallowing worker task cancellation
- Docs
- Python not yet supported