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.
Latest release v0.24.0 · 15 Oct 2026
16 files for Codex, Claude Code and OpenCode: code-change-verification, docs-sync, examples-run-analysis, final-release-review and 12 more — 7,131 tokens loaded in every session.
AGENTS.md A 7,128 tok CLAUDE.md A 3 tok .agents/skills/code-change-verification/SKILL.md A 25 tok .agents/skills/docs-sync/SKILL.md A 15 tok .agents/skills/examples-run-analysis/SKILL.md A 21 tok .agents/skills/final-release-review/SKILL.md A 23 tok .agents/skills/implementation-final-review/SKILL.md A 26 tok .agents/skills/implementation-kickoff/SKILL.md A 26 tok .agents/skills/implementation-strategy/SKILL.md A 22 tok .agents/skills/maintainer-review/SKILL.md A 29 tok .agents/skills/openai-knowledge/SKILL.md B 23 tok .agents/skills/pr-draft-summary/SKILL.md A 24 tok .agents/skills/release-candidate-prep/SKILL.md A 28 tok .agents/skills/runtime-behavior-probe/SKILL.md A 23 tok .agents/skills/sensitive-logging-audit/SKILL.md A 25 tok .agents/skills/test-coverage-improver/SKILL.md A 31 tok 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.