← Browse tools

Agent frameworks

OpenAI Agents SDK

Small explicit primitive set that relies on normal Python control flow rather than a heavy orchestration DSL.

Overview

Research summary

OpenAI Agents SDK is an MIT-licensed Python framework for building agentic applications around a deliberately small set of primitives. Agents combine instructions, models and tools; handoffs and agents-as-tools support delegation between specialized agents; guardrails validate selected inputs and outputs; and the runtime includes sessions, streaming and tracing for inspecting executions. The SDK is designed to let normal Python control flow own application structure rather than requiring every workflow to be represented by a large framework-specific graph or configuration language.

Although it integrates most directly with OpenAI models and platform capabilities, the framework layer is distinct from the hosted models and APIs that execute requests. The repository is therefore useful both as an implementation toolkit and as a reference for a relatively minimal agent-runtime design. OpenAI service usage, model access and tracing backends retain their own operational and commercial terms.

Repository summary

Stars
29,491
Open issues
Unavailable
Last push
2026-09-16
Commits, 90 days
Unavailable
Repository activity
Not scored
Version
Unavailable

Recorded catalogue figures. View repository data and provenance →

Classification

Pricing & services

Paid services unknown

Whether the provider offers paid products or services has not been established.

Licence scope

Implementation

Recorded implementation details and interfaces for OpenAI Agents SDK.

Implementation details

Python agent runtime and SDK

Languages
Python
Repository type
source

Recorded interfaces and capabilities

Licence scope

Repository

Repository snapshots, release information and recorded maintenance signals.

Repository snapshot

openai/openai-agents-python ↗

Stars
29,491
Open issues
Unavailable
Last push
2026-09-16
Commits, 90 days
Unavailable
Repository activity
Not scored
Archived
Not recorded

Repository activity is a snapshot, not a quality or popularity ranking. It combines recent-push freshness (50%), 90-day commits (30%) and issue pressure (20%).

Maintenance and provenance

Catalogue snapshot
2026-10-06
Stars source
Recorded fallback
Last push source
Recorded fallback

Documentation

Recorded references and research provenance for this entry.

Recorded sources 3

Research metadata

Research date
2026-09-16
Catalogue snapshot
2026-10-06