A lightweight, powerful framework for multi-agent workflows
OpenAI Agents SDK is a Python framework for building workflows in which multiple AI agents use tools, delegate tasks, follow safety checks, and involve people when needed. Developers use it to create and monitor agent, sandbox, realtime, and voice applications.
These files are openai/openai-agents-python's own configuration. They tell Codex, Claude Code and OpenCode how to work on this repository, so they are not mods to install elsewhere. Copy one as a starting point and replace the parts that are about this project.
AGENTS.md A 8,006 tok CLAUDE.md A 3 tok .agents/skills/code-change-verification/SKILL.md A 30 tok .agents/skills/docs-sync/SKILL.md A 79 tok .agents/skills/examples-run-analysis/SKILL.md A 52 tok .agents/skills/final-release-review/SKILL.md A 64 tok .agents/skills/implementation-final-review/SKILL.md A 58 tok .agents/skills/implementation-kickoff/SKILL.md A 113 tok .agents/skills/implementation-strategy/SKILL.md A 47 tok .agents/skills/maintainer-review/SKILL.md A 69 tok .agents/skills/openai-knowledge/SKILL.md B 83 tok .agents/skills/pr-draft-summary/SKILL.md A 114 tok .agents/skills/release-candidate-prep/SKILL.md A 87 tok .agents/skills/runtime-behavior-probe/SKILL.md A 53 tok .agents/skills/sensitive-logging-audit/SKILL.md A 59 tok .agents/skills/test-coverage-improver/SKILL.md A 47 tok