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 supported1 Subscribers
Add a CodeTriage badge to openai-agents-python
Help out
- Issues
- Anthropic caching not supported on LiteLLM
- Chat Completions: Immediately return `ResponseReasoningSummaryPartDoneEvent` event when `reasoning_content` ends
- Calling MCP server tools with nested object params from Realtime API agents
- Customizing traces and spans: Ability to add metadata to spans
- nest handoff: Handoff is incompatible with server-managed conversation
- Release 0.8.0
- fix: #2386 offload sync tool execution to worker threads
- fix: make trace_include_sensitive_data default to False for security
- Security: trace_include_sensitive_data defaults to True, risking accidental data exposure
- pre_handoff_items
- Docs
- Python not yet supported