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
- List Sprites as a hosted sandbox platform
- SessionSettings(limit=N) window can start inside a reasoning response, so the Responses API rejects the turn
- AnyLLMModel chat completions: extra_headers TypeError on Mistral (Chat.complete_async)
- Voice: default sentence splitter never splits Chinese/Japanese, so TTS waits for the whole reply
- Feature proposal: inherited recursion-depth budget for Agent.as_tool delegation
- Chat Completions models drop the conversation history when conversation_id/previous_response_id are set
- OpenAIChatCompletionsModel sends max_tokens, which reasoning models reject
- Pattern: deterministic self-verification of numeric claims via a function tool
- Streamed Chat Completions turns report response_id '__fake_id__' instead of None, and it leaks into previous_response_id and compaction
- function_tool rejects valid arguments when a parameter uses Pydantic strict mode (Enum, date, UUID)
- Docs
- Python not yet supported